Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1409. Min Act: -0.0002

Data Index: 409535 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0002

Data Index: 374825 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1405. Min Act: -0.0002

Data Index: 706949 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1231. Min Act: -0.0002

Data Index: 812280 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1245888 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1159. Min Act: -0.0002

Data Index: 625344 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1325985 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1143. Min Act: -0.0003

Data Index: 1083326 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1075. Min Act: -0.0002

Data Index: 669326 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1050. Min Act: -0.0002

Data Index: 34117 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1005. Min Act: -0.0002

Data Index: 508197 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1114256 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1262296 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1015. Min Act: -0.0002

Data Index: 752052 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1050. Min Act: -0.0002

Data Index: 239018 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1007. Min Act: -0.0002

Data Index: 374076 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0988. Min Act: -0.0002

Data Index: 969324 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1178314 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1121145 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0975. Min Act: -0.0002

Data Index: 336389 (C4 (Web Text))

Max Activating Token Index: 740