Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.1213. Min Act: -0.0003

Data Index: 1079377 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.1406. Min Act: -0.0003

Data Index: 134900 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.0767. Min Act: -0.0003

Data Index: 487253 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.0862. Min Act: -0.0003

Data Index: 986895 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.0589. Min Act: -0.0003

Data Index: 65854 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.0213. Min Act: -0.0003

Data Index: 840476 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9056. Min Act: -0.0003

Data Index: 491746 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8876. Min Act: -0.0003

Data Index: 603879 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 1.1406. Min Range: -1.1406

Max Act: 1.0198. Min Act: -0.0003

Data Index: 1004288 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9691. Min Act: -0.0003

Data Index: 1036445 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9188. Min Act: -0.0003

Data Index: 269255 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9239. Min Act: -0.0003

Data Index: 802624 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9238. Min Act: -0.0003

Data Index: 191989 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9664. Min Act: -0.0003

Data Index: 876501 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.9380. Min Act: -0.0003

Data Index: 1222909 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8997. Min Act: -0.0003

Data Index: 594168 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8945. Min Act: -0.0003

Data Index: 99691 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8626. Min Act: -0.0003

Data Index: 546556 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8884. Min Act: -0.0003

Data Index: 402481 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.1406. Min Range: -1.1406

Max Act: 0.8917. Min Act: -0.0003

Data Index: 1151293 (C4 (Web Text))

Max Activating Token Index: 500