Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.3796. Min Act: -0.0000

Data Index: 1287246 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.6260. Min Act: -0.0000

Data Index: 1028563 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.3922. Min Act: -0.0000

Data Index: 312945 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.2672. Min Act: -0.0000

Data Index: 846162 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.2586. Min Act: -0.0000

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.0028. Min Act: -0.0000

Data Index: 701124 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.8036. Min Act: -0.0000

Data Index: 537702 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.9249. Min Act: -0.0000

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.9500. Min Act: -0.0000

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 4.6260. Min Range: -4.6260

Max Act: 4.0207. Min Act: -0.0000

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.6404. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.9539. Min Act: -0.0000

Data Index: 400486 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.5132. Min Act: -0.0000

Data Index: 208071 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.4925. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.3248. Min Act: -0.0000

Data Index: 510189 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.6262. Min Act: -0.0000

Data Index: 1155032 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.2925. Min Act: -0.0000

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.7191. Min Act: -0.0000

Data Index: 160606 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.3679. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 4.6260. Min Range: -4.6260

Max Act: 3.4552. Min Act: -0.0000

Data Index: 977504 (C4 (Web Text))

Max Activating Token Index: 836