< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 5 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1396417 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.6280. Min Act: -0.0001

Data Index: 1203188 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5818. Min Act: -0.0001

Data Index: 242170 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.6158. Min Act: -0.0001

Data Index: 509623 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5414. Min Act: -0.0001

Data Index: 1093515 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5608. Min Act: -0.0001

Data Index: 1956382 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1153213 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1122386 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5347. Min Act: -0.0001

Data Index: 468242 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5094. Min Act: -0.0001

Data Index: 1739497 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1668496 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1082347 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1957616 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1876292 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4675. Min Act: -0.0001

Data Index: 970191 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4368. Min Act: -0.0001

Data Index: 951902 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1562637 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4462. Min Act: -0.0001

Data Index: 1366203 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4415. Min Act: -0.0001

Data Index: 528810 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6383. Min Range: -0.6383

Max Act: 0.4513. Min Act: -0.0001

Data Index: 752751 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #19