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

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

Neuron 641 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: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1517501 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0226. Min Act: -0.0003

Data Index: 810032 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1498321 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0003

Data Index: 265768 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1389774 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1597105 (Python Code)

Max Activating Token Index: 760

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0202. Min Act: -0.0003

Data Index: 358088 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1534216 (Python Code)

Max Activating Token Index: 807

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1473759 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0194. Min Act: -0.0003

Data Index: 462727 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1455048 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1088196 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1533021 (Python Code)

Max Activating Token Index: 1008

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0197. Min Act: -0.0003

Data Index: 267749 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 213689 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1024301 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1638846 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0159. Min Act: -0.0003

Data Index: 273852 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1569308 (Python Code)

Max Activating Token Index: 582