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

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

Neuron 3515 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: 0.7133. Min Range: -0.7133

Max Act: 0.7133. Min Act: -0.0001

Data Index: 973915 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.7051. Min Act: -0.0001

Data Index: 548053 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6236. Min Act: -0.0001

Data Index: 1130541 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6282. Min Act: -0.0001

Data Index: 800161 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6231. Min Act: -0.0001

Data Index: 41355 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5993. Min Act: -0.0001

Data Index: 455125 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5919. Min Act: -0.0001

Data Index: 312875 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6212. Min Act: -0.0001

Data Index: 460194 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6003. Min Act: -0.0001

Data Index: 19491 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6176. Min Act: -0.0001

Data Index: 172151 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1175770 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5925. Min Act: -0.0001

Data Index: 715205 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5834. Min Act: -0.0001

Data Index: 1114863 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6075. Min Act: -0.0001

Data Index: 83973 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5695. Min Act: -0.0001

Data Index: 842802 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1001138 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5610. Min Act: -0.0001

Data Index: 323811 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5401. Min Act: -0.0001

Data Index: 468581 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5719. Min Act: -0.0001

Data Index: 254818 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5506. Min Act: -0.0001

Data Index: 178000 (C4 (Web Text))

Max Activating Token Index: 366