< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 30 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.1323. Min Range: -1.1323

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1950759 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.1323. Min Range: -1.1323

Max Act: 1.0347. Min Act: -0.0001

Data Index: 1971385 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.1323. Min Range: -1.1323

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1253374 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9942. Min Act: -0.0001

Data Index: 902240 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9575. Min Act: -0.0001

Data Index: 491661 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9774. Min Act: -0.0001

Data Index: 678766 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9150. Min Act: -0.0001

Data Index: 1259942 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9463. Min Act: -0.0001

Data Index: 617520 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1577608 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9053. Min Act: -0.0001

Data Index: 1010071 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8943. Min Act: -0.0001

Data Index: 1535497 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8942. Min Act: -0.0001

Data Index: 1594775 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9519. Min Act: -0.0001

Data Index: 761444 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9316. Min Act: -0.0001

Data Index: 855446 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.9120. Min Act: -0.0001

Data Index: 879363 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8669. Min Act: -0.0001

Data Index: 1202379 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8315. Min Act: -0.0001

Data Index: 865086 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8663. Min Act: -0.0001

Data Index: 1780540 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.7852. Min Act: -0.0001

Data Index: 916602 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.1323. Min Range: -1.1323

Max Act: 0.8683. Min Act: -0.0001

Data Index: 952175 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #19