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

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

Neuron 5002 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: 0.5932. Min Range: -0.5932

Max Act: 0.5932. Min Act: -0.0000

Data Index: 749626 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1120113 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5432. Min Act: -0.0000

Data Index: 337541 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1277901 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4889. Min Act: -0.0000

Data Index: 96805 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4507. Min Act: -0.0000

Data Index: 139759 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4228. Min Act: -0.0000

Data Index: 933116 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1330190 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4380. Min Act: -0.0000

Data Index: 785968 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4326. Min Act: -0.0000

Data Index: 973211 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4025. Min Act: -0.0000

Data Index: 357825 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1265936 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1133211 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3955. Min Act: -0.0000

Data Index: 428027 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4125. Min Act: -0.0000

Data Index: 327668 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4297. Min Act: -0.0000

Data Index: 911545 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3789. Min Act: -0.0000

Data Index: 473337 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1138349 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3945. Min Act: -0.0000

Data Index: 433188 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.5932. Min Range: -0.5932

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1279730 (C4 (Web Text))

Max Activating Token Index: 324