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

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

Neuron 4742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.5348. Min Act: -0.0000

Data Index: 208975 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1014439 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.5114. Min Act: -0.0000

Data Index: 185367 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.5178. Min Act: -0.0000

Data Index: 649376 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1136199 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4695. Min Act: -0.0000

Data Index: 57606 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4438. Min Act: -0.0000

Data Index: 143878 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1221539 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4080. Min Act: -0.0000

Data Index: 864413 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4165. Min Act: -0.0000

Data Index: 600402 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4129. Min Act: -0.0000

Data Index: 773296 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4227. Min Act: -0.0000

Data Index: 43610 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4225. Min Act: -0.0000

Data Index: 807556 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3984. Min Act: 0.0000

Data Index: 739023 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4006. Min Act: -0.0000

Data Index: 49263 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4144. Min Act: -0.0000

Data Index: 36525 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1126856 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3983. Min Act: -0.0000

Data Index: 339294 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.4149. Min Act: -0.0000

Data Index: 554552 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.5348. Min Range: -0.5348

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1348789 (C4 (Web Text))

Max Activating Token Index: 205