Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 977 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1481759 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1603220 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0214. Min Act: -0.0002

Data Index: 939744 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0200. Min Act: -0.0002

Data Index: 339053 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1276927 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1467295 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0185. Min Act: -0.0002

Data Index: 497275 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0171. Min Act: -0.0002

Data Index: 135108 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0164. Min Act: -0.0002

Data Index: 602661 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0166. Min Act: -0.0002

Data Index: 323210 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1607647 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1209710 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0166. Min Act: -0.0002

Data Index: 466207 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1240806 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0166. Min Act: -0.0002

Data Index: 261076 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1531831 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0163. Min Act: -0.0002

Data Index: 551763 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0160. Min Act: -0.0002

Data Index: 978879 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1490990 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1242232 (C4 (Web Text))

Max Activating Token Index: 910