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

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

Neuron 2409 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1634. Min Act: -0.0002

Data Index: 63590 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1375. Min Act: -0.0002

Data Index: 735294 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1355421 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1319003 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1281. Min Act: -0.0002

Data Index: 758102 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1354980 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1270. Min Act: -0.0002

Data Index: 655252 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1229. Min Act: -0.0001

Data Index: 159543 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1103. Min Act: -0.0002

Data Index: 653962 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1255. Min Act: -0.0001

Data Index: 929953 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1117653 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1126637 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1047605 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1182. Min Act: -0.0002

Data Index: 579553 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1147073 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1060. Min Act: -0.0001

Data Index: 752361 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1007233 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1103. Min Act: -0.0002

Data Index: 47778 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.1087. Min Act: -0.0002

Data Index: 364463 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.1634. Min Range: -0.1634

Max Act: 0.0945. Min Act: -0.0001

Data Index: 911120 (C4 (Web Text))

Max Activating Token Index: 371