Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5351. Min Act: -0.0000

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5235. Min Act: -0.0000

Data Index: 824917 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1227508 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4699. Min Act: -0.0000

Data Index: 606435 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1087985 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.5217. Min Act: -0.0000

Data Index: 897776 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1034469 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4636. Min Act: -0.0000

Data Index: 18407 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4572. Min Act: -0.0000

Data Index: 965525 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4224. Min Act: -0.0000

Data Index: 245385 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4020. Min Act: -0.0000

Data Index: 979791 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1256477 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1644957 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4467. Min Act: -0.0000

Data Index: 176435 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4292. Min Act: -0.0000

Data Index: 906464 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3859. Min Act: -0.0000

Data Index: 460283 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.4355. Min Act: -0.0000

Data Index: 316091 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3956. Min Act: -0.0000

Data Index: 985849 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.5351. Min Range: -0.5351

Max Act: 0.3822. Min Act: -0.0000

Data Index: 666579 (C4 (Web Text))

Max Activating Token Index: 945