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

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

Neuron 3713 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.9453. Min Act: -0.0001

Data Index: 179483 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5905. Min Act: -0.0001

Data Index: 35724 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5211. Min Act: -0.0001

Data Index: 337435 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4613. Min Act: -0.0001

Data Index: 239967 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4717. Min Act: -0.0001

Data Index: 179003 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4339. Min Act: -0.0001

Data Index: 595679 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4388. Min Act: -0.0001

Data Index: 282158 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4473. Min Act: -0.0001

Data Index: 332900 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4160. Min Act: -0.0001

Data Index: 74419 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4025. Min Act: -0.0001

Data Index: 1306278 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.3710. Min Act: -0.0001

Data Index: 1087430 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4098. Min Act: -0.0001

Data Index: 866690 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4254. Min Act: -0.0001

Data Index: 982027 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.3913. Min Act: -0.0001

Data Index: 498678 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4185. Min Act: -0.0001

Data Index: 275384 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.3728. Min Act: -0.0001

Data Index: 538402 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4097. Min Act: -0.0001

Data Index: 574913 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.3978. Min Act: -0.0001

Data Index: 685843 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4081. Min Act: -0.0001

Data Index: 944981 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.3831. Min Act: -0.0001

Data Index: 637306 (C4 (Web Text))

Max Activating Token Index: 1018