Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1475 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1178. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0978. Min Act: -0.0001

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1167. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1115. Min Act: -0.0001

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1085. Min Act: -0.0001

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1431430 (Python Code)

Max Activating Token Index: 568

Text #9

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1515445 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1383200 (Python Code)

Max Activating Token Index: 511

Text #11

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1474955 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1107. Min Act: -0.0001

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1078825 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1102. Min Act: -0.0001

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1069. Min Act: -0.0000

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0996. Min Act: -0.0001

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1560626 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 0.1403. Min Range: -0.1403

Max Act: 0.1055. Min Act: -0.0001

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 171