Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 447 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0253. Min Act: -0.0003

Data Index: 5704 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0269. Min Act: -0.0003

Data Index: 17166 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0269. Min Act: -0.0004

Data Index: 200683 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0003

Data Index: 856725 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0250. Min Act: -0.0003

Data Index: 809244 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0264. Min Act: -0.0003

Data Index: 158222 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0259. Min Act: -0.0003

Data Index: 160032 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0259. Min Act: -0.0004

Data Index: 841670 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0266. Min Act: -0.0003

Data Index: 683869 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1350900 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1157137 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0250. Min Act: -0.0003

Data Index: 365689 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1124107 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0233. Min Act: -0.0004

Data Index: 125562 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0249. Min Act: -0.0003

Data Index: 530277 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1106801 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1019164 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1063626 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0231. Min Act: -0.0003

Data Index: 584286 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0003

Data Index: 702999 (C4 (Web Text))

Max Activating Token Index: 741