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

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

Neuron 3887 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: 0.7173. Min Range: -0.7173

Max Act: 0.7173. Min Act: -0.0000

Data Index: 194159 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6875. Min Act: -0.0000

Data Index: 783458 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5961. Min Act: 0.0000

Data Index: 237425 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5894. Min Act: -0.0000

Data Index: 724984 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5865. Min Act: -0.0000

Data Index: 182048 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5534. Min Act: 0.0001

Data Index: 754268 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1281674 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1218185 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6049. Min Act: 0.0000

Data Index: 72907 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5421. Min Act: -0.0000

Data Index: 679255 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5478. Min Act: -0.0000

Data Index: 943415 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5261. Min Act: -0.0000

Data Index: 790632 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5402. Min Act: -0.0000

Data Index: 273363 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5027. Min Act: 0.0000

Data Index: 1275674 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5292. Min Act: 0.0000

Data Index: 1175754 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1313937 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5104. Min Act: 0.0000

Data Index: 807468 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5076. Min Act: -0.0000

Data Index: 452895 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5026. Min Act: -0.0000

Data Index: 749146 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5019. Min Act: 0.0000

Data Index: 262601 (C4 (Web Text))

Max Activating Token Index: 166