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

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

Neuron 404 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: 0.1468. Min Range: -0.1468

Max Act: 0.1349. Min Act: -0.0002

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1333210 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1188. Min Act: -0.0002

Data Index: 943896 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1423. Min Act: -0.0001

Data Index: 745093 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0002

Data Index: 256095 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1339. Min Act: -0.0001

Data Index: 385623 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1110379 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1298. Min Act: -0.0002

Data Index: 309830 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1268499 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1235. Min Act: -0.0002

Data Index: 38925 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1182. Min Act: -0.0001

Data Index: 665347 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1203. Min Act: -0.0002

Data Index: 523382 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1110. Min Act: -0.0001

Data Index: 349986 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1175. Min Act: -0.0001

Data Index: 158076 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1130. Min Act: -0.0002

Data Index: 748173 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1130316 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1071. Min Act: -0.0002

Data Index: 1157671 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1190. Min Act: -0.0002

Data Index: 293744 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1026010 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0988. Min Act: -0.0002

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 239