Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 706 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0003

Data Index: 812077 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1476442 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0258. Min Act: -0.0003

Data Index: 414860 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1526348 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0261. Min Act: -0.0000

Data Index: 779551 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1248156 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1128403 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1528514 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0249. Min Act: -0.0003

Data Index: 674090 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1447247 (Python Code)

Max Activating Token Index: 485

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1127174 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1314021 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1545356 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1548390 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0250. Min Act: -0.0000

Data Index: 1044926 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1577295 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1626730 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0248. Min Act: -0.0002

Data Index: 985657 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0250. Min Act: -0.0003

Data Index: 447841 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1419221 (Python Code)

Max Activating Token Index: 473