Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0305. Min Act: 0.0001

Data Index: 998063 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 278033 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0302. Min Act: -0.0002

Data Index: 363102 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1312948 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0273. Min Act: -0.0002

Data Index: 20012 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0002

Data Index: 673118 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1137122 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1175107 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 19870 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 788560 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0254. Min Act: -0.0002

Data Index: 203570 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0268. Min Act: -0.0002

Data Index: 18035 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0002

Data Index: 899127 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0002

Data Index: 187987 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0265. Min Act: -0.0001

Data Index: 809502 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1224238 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0264. Min Act: -0.0001

Data Index: 879386 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0258. Min Act: -0.0002

Data Index: 753642 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1073126 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1305667 (C4 (Web Text))

Max Activating Token Index: 667