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

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

Neuron 1143 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8394. Min Act: -0.0000

Data Index: 901021 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8167. Min Act: -0.0000

Data Index: 620963 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7551. Min Act: -0.0000

Data Index: 84445 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1212517 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7846. Min Act: -0.0000

Data Index: 430222 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7838. Min Act: -0.0000

Data Index: 237243 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7739. Min Act: -0.0000

Data Index: 831803 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7601. Min Act: -0.0000

Data Index: 605339 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7434. Min Act: -0.0000

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7564. Min Act: -0.0000

Data Index: 439954 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7420. Min Act: -0.0000

Data Index: 636767 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1221128 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1333119 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7222. Min Act: -0.0000

Data Index: 925654 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7196. Min Act: -0.0000

Data Index: 686817 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.7122. Min Act: -0.0000

Data Index: 209157 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1134859 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6513. Min Act: -0.0000

Data Index: 934958 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6834. Min Act: -0.0000

Data Index: 572180 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6791. Min Act: -0.0000

Data Index: 109728 (C4 (Web Text))

Max Activating Token Index: 745