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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1275 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.8197. Min Act: -0.0001

Data Index: 668600 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.5244. Min Act: -0.0002

Data Index: 1094937 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4324. Min Act: -0.0001

Data Index: 791289 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3493. Min Act: -0.0001

Data Index: 1079188 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4860. Min Act: -0.0001

Data Index: 653309 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4787. Min Act: -0.0001

Data Index: 1106300 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4358. Min Act: -0.0001

Data Index: 645147 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4335. Min Act: -0.0001

Data Index: 1163532 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3568. Min Act: -0.0001

Data Index: 782215 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3960. Min Act: -0.0001

Data Index: 758950 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3584. Min Act: -0.0001

Data Index: 686268 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3545. Min Act: -0.0001

Data Index: 33678 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.2381. Min Act: -0.0001

Data Index: 470200 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3187. Min Act: -0.0001

Data Index: 507049 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.4882. Min Act: -0.0001

Data Index: 72168 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3695. Min Act: -0.0001

Data Index: 1643772 (Python Code)

Max Activating Token Index: 823

Text #16

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.1829. Min Act: -0.0001

Data Index: 810140 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.2489. Min Act: -0.0001

Data Index: 188182 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3824. Min Act: -0.0001

Data Index: 382924 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.8197. Min Range: -1.8197

Max Act: 1.3154. Min Act: -0.0001

Data Index: 241291 (C4 (Web Text))

Max Activating Token Index: 281