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

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

Neuron 5930 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0000

Data Index: 988165 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1723. Min Act: -0.0000

Data Index: 229811 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1761. Min Act: -0.0000

Data Index: 898171 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1591. Min Act: -0.0000

Data Index: 590208 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1215181 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1384. Min Act: -0.0000

Data Index: 177806 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1268. Min Act: -0.0000

Data Index: 728226 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1245. Min Act: -0.0000

Data Index: 140785 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1282. Min Act: -0.0000

Data Index: 852232 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1187. Min Act: -0.0000

Data Index: 650263 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1358. Min Act: -0.0000

Data Index: 628470 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1256486 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1228. Min Act: -0.0000

Data Index: 90440 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1221. Min Act: -0.0000

Data Index: 381545 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1186472 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1216. Min Act: -0.0000

Data Index: 200066 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1154. Min Act: -0.0000

Data Index: 846762 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1198. Min Act: -0.0000

Data Index: 573085 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1171. Min Act: -0.0000

Data Index: 219093 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1007. Min Act: -0.0000

Data Index: 707420 (C4 (Web Text))

Max Activating Token Index: 901