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

Dataset: The Pile

Neuron 1876 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1157800 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.9214. Min Act: -0.0000

Data Index: 947805 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1321463 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8738. Min Act: -0.0000

Data Index: 211270 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8162. Min Act: -0.0000

Data Index: 461383 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1768839 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1088957 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6901. Min Act: -0.0000

Data Index: 139378 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6896. Min Act: -0.0000

Data Index: 799085 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7049. Min Act: -0.0000

Data Index: 553126 (The Pile)

Max Activating Token Index: 659

Text #10

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7277. Min Act: -0.0000

Data Index: 909045 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1393386 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1080580 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1980280 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.8019. Min Act: -0.0000

Data Index: 588493 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6770. Min Act: -0.0000

Data Index: 319686 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.7418. Min Act: -0.0000

Data Index: 208689 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1398189 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6306. Min Act: -0.0000

Data Index: 557252 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.9352. Min Range: -0.9352

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1838072 (The Pile)

Max Activating Token Index: 641