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

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

Neuron 5901 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1232718 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1530. Min Act: -0.0000

Data Index: 703188 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1284139 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1417. Min Act: -0.0000

Data Index: 550261 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1415. Min Act: -0.0000

Data Index: 721122 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1326. Min Act: -0.0000

Data Index: 244251 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1365. Min Act: -0.0000

Data Index: 316256 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1320. Min Act: -0.0000

Data Index: 866636 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1316. Min Act: -0.0000

Data Index: 46914 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1197. Min Act: -0.0000

Data Index: 59267 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1169. Min Act: -0.0000

Data Index: 30246 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1204. Min Act: -0.0000

Data Index: 396765 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1122844 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1194. Min Act: -0.0000

Data Index: 118095 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1142221 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1183. Min Act: -0.0000

Data Index: 729197 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1110. Min Act: -0.0000

Data Index: 280103 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1069. Min Act: -0.0000

Data Index: 112182 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1110. Min Act: -0.0000

Data Index: 240078 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1737. Min Range: -0.1737

Max Act: 0.1104. Min Act: -0.0000

Data Index: 999590 (C4 (Web Text))

Max Activating Token Index: 62