< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.3394. Min Act: -0.0000

Data Index: 44838 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1222707 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.2457. Min Act: -0.0000

Data Index: 286225 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3394. Min Range: -2.3394

Max Act: 2.1225. Min Act: -0.0000

Data Index: 1020874 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6935. Min Act: -0.0000

Data Index: 1485607 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.8364. Min Act: -0.0000

Data Index: 387091 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1525866 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.7156. Min Act: -0.0000

Data Index: 1082394 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6237. Min Act: -0.0000

Data Index: 963326 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4274. Min Act: -0.0000

Data Index: 577658 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1566854 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.7207. Min Act: -0.0000

Data Index: 1279020 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6336. Min Act: -0.0000

Data Index: 1661200 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1894670 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6307. Min Act: -0.0000

Data Index: 1378399 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5891. Min Act: -0.0000

Data Index: 454777 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1910189 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.6948. Min Act: -0.0000

Data Index: 1555983 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5629. Min Act: -0.0000

Data Index: 493775 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3394. Min Range: -2.3394

Max Act: 1.5669. Min Act: -0.0000

Data Index: 562828 (The Pile)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #19