Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1270380 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0224. Min Act: -0.0005

Data Index: 882805 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1292596 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0214. Min Act: -0.0005

Data Index: 816519 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0005

Data Index: 556178 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0005

Data Index: 1309989 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0210. Min Act: -0.0005

Data Index: 1235125 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0005

Data Index: 55139 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0206. Min Act: -0.0005

Data Index: 860980 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0005

Data Index: 813177 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0206. Min Act: -0.0005

Data Index: 308482 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0209. Min Act: -0.0005

Data Index: 778048 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0005

Data Index: 971312 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0005

Data Index: 131886 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0005

Data Index: 929729 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0005

Data Index: 436346 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1168281 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0005

Data Index: 638319 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1292136 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0197. Min Act: -0.0005

Data Index: 646649 (C4 (Web Text))

Max Activating Token Index: 526