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

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

Neuron 2719 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: 0.0337. Min Range: -0.0337

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1400534 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1227334 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0321. Min Act: -0.0003

Data Index: 884399 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1381519 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0298. Min Act: -0.0003

Data Index: 43011 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0306. Min Act: -0.0003

Data Index: 112098 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1057046 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0003

Data Index: 98581 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0321. Min Act: -0.0003

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0295. Min Act: -0.0003

Data Index: 422526 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1359593 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0306. Min Act: -0.0003

Data Index: 463852 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0291. Min Act: -0.0003

Data Index: 277460 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1484813 (Python Code)

Max Activating Token Index: 559

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0306. Min Act: -0.0003

Data Index: 86671 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0312. Min Act: -0.0003

Data Index: 450963 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0312. Min Act: -0.0003

Data Index: 184249 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0286. Min Act: -0.0003

Data Index: 209210 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1456198 (Python Code)

Max Activating Token Index: 898

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0248. Min Act: -0.0003

Data Index: 220353 (C4 (Web Text))

Max Activating Token Index: 629