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

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

Neuron 4095 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0002

Data Index: 129086 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1319107 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1154. Min Act: -0.0001

Data Index: 674187 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1195. Min Act: -0.0001

Data Index: 906181 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1204. Min Act: -0.0002

Data Index: 245858 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1037. Min Act: -0.0001

Data Index: 324455 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1118. Min Act: -0.0002

Data Index: 66942 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1054. Min Act: -0.0002

Data Index: 330037 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1110. Min Act: -0.0002

Data Index: 118453 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1048. Min Act: -0.0001

Data Index: 607823 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0998. Min Act: -0.0001

Data Index: 961947 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1052. Min Act: -0.0001

Data Index: 334449 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1164188 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1057. Min Act: -0.0002

Data Index: 998050 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1046. Min Act: -0.0002

Data Index: 750161 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1051. Min Act: -0.0002

Data Index: 809494 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1465513 (Python Code)

Max Activating Token Index: 431

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0921. Min Act: -0.0002

Data Index: 86465 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0951. Min Act: -0.0002

Data Index: 119016 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0955. Min Act: -0.0002

Data Index: 534789 (C4 (Web Text))

Max Activating Token Index: 753