Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 786 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1097352 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0203. Min Act: -0.0006

Data Index: 258959 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1271721 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0198. Min Act: -0.0006

Data Index: 991372 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0200. Min Act: -0.0006

Data Index: 814980 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1034918 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0188. Min Act: -0.0006

Data Index: 189342 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0177. Min Act: -0.0006

Data Index: 91539 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0193. Min Act: -0.0006

Data Index: 636813 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0187. Min Act: -0.0006

Data Index: 860724 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0179. Min Act: -0.0006

Data Index: 744111 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0186. Min Act: -0.0006

Data Index: 215755 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0174. Min Act: -0.0006

Data Index: 478544 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0182. Min Act: -0.0006

Data Index: 617564 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1234137 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0175. Min Act: -0.0006

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1086091 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0187. Min Act: -0.0006

Data Index: 248123 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1148211 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0176. Min Act: -0.0006

Data Index: 144813 (C4 (Web Text))

Max Activating Token Index: 348