Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1835 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0002

Data Index: 385338 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1313. Min Act: -0.0002

Data Index: 1027494 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1182. Min Act: -0.0001

Data Index: 849706 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1061271 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1167. Min Act: -0.0002

Data Index: 189336 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1170. Min Act: -0.0002

Data Index: 972575 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1153. Min Act: -0.0002

Data Index: 970445 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1159. Min Act: -0.0002

Data Index: 745404 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1154. Min Act: -0.0002

Data Index: 290660 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1092352 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1052. Min Act: -0.0002

Data Index: 960419 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1099. Min Act: -0.0002

Data Index: 346618 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1070. Min Act: -0.0002

Data Index: 321997 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1110373 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1067. Min Act: -0.0002

Data Index: 979013 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1009. Min Act: -0.0002

Data Index: 963481 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1088. Min Act: -0.0002

Data Index: 105650 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1344531 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1020. Min Act: -0.0002

Data Index: 459690 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1308855 (C4 (Web Text))

Max Activating Token Index: 52