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

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

Neuron 1335 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1257195 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0001

Data Index: 689954 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1509554 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1526257 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0234. Min Act: -0.0001

Data Index: 181003 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1075334 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0210. Min Act: -0.0001

Data Index: 760157 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0147. Min Act: -0.0001

Data Index: 208150 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1447480 (Python Code)

Max Activating Token Index: 183

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1547116 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1119373 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0001

Data Index: 326224 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0001

Data Index: 128848 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0214. Min Act: -0.0001

Data Index: 1589851 (Python Code)

Max Activating Token Index: 818

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1068078 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0204. Min Act: -0.0001

Data Index: 1498482 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1193654 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1372754 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0201. Min Act: -0.0001

Data Index: 203688 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1110866 (C4 (Web Text))

Max Activating Token Index: 158