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

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

Neuron 3385 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8288. Min Range: -1.8288

Max Act: 1.8288. Min Act: -0.0000

Data Index: 136151 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.8288. Min Range: -1.8288

Max Act: 1.2360. Min Act: -0.0000

Data Index: 696719 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.8288. Min Range: -1.8288

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1224197 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.8288. Min Range: -1.8288

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1035205 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 1.8288. Min Range: -1.8288

Max Act: 1.1106. Min Act: -0.0000

Data Index: 523004 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.8969. Min Act: -0.0000

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.7633. Min Act: 0.0000

Data Index: 674829 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.8132. Min Act: 0.0000

Data Index: 165108 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1139125 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6227. Min Act: -0.0000

Data Index: 940493 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6838. Min Act: -0.0000

Data Index: 25071 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6962. Min Act: -0.0000

Data Index: 329033 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6091. Min Act: -0.0000

Data Index: 79436 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6755. Min Act: -0.0000

Data Index: 836763 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.5888. Min Act: -0.0000

Data Index: 772202 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1035173 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.5677. Min Act: -0.0000

Data Index: 129976 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.5737. Min Act: 0.0000

Data Index: 88947 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.5490. Min Act: 0.0000

Data Index: 515759 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.8288. Min Range: -1.8288

Max Act: 0.6191. Min Act: -0.0000

Data Index: 578421 (C4 (Web Text))

Max Activating Token Index: 599