Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.6091. Min Act: -0.0000

Data Index: 150288 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4491. Min Act: -0.0000

Data Index: 633121 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1001682 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1933970 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1563767 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1572581 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1980539 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1363407 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1427369 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1373189 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3270. Min Act: -0.0000

Data Index: 380073 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1958510 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1660854 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1873949 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3161. Min Act: -0.0000

Data Index: 370373 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1770040 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1860858 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1618197 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.3045. Min Act: -0.0000

Data Index: 78415 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.6091. Min Range: -0.6091

Max Act: 0.2879. Min Act: -0.0000

Data Index: 832567 (The Pile)

Max Activating Token Index: 89