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

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

Neuron 18 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.8173. Min Act: -0.0000

Data Index: 108578 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.7142. Min Act: -0.0000

Data Index: 787561 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.6252. Min Act: -0.0000

Data Index: 58942 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1114226 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.4642. Min Act: -0.0001

Data Index: 323913 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1226785 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.3965. Min Act: -0.0001

Data Index: 1251736 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.3566. Min Act: -0.0000

Data Index: 818137 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1186982 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.4147. Min Act: -0.0000

Data Index: 289243 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.2468. Min Act: -0.0000

Data Index: 407734 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.2535. Min Act: -0.0000

Data Index: 706396 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.2408. Min Act: -0.0000

Data Index: 234329 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.3239. Min Act: -0.0000

Data Index: 886993 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.1222. Min Act: -0.0000

Data Index: 289415 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1272671 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.1146. Min Act: -0.0000

Data Index: 515966 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.1275. Min Act: -0.0000

Data Index: 993027 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.0833. Min Act: -0.0000

Data Index: 656747 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 1.8173. Min Range: -1.8173

Max Act: 1.0914. Min Act: -0.0001

Data Index: 1340483 (C4 (Web Text))

Max Activating Token Index: 961