Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1207. Min Act: -0.0002

Data Index: 845585 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1093. Min Act: -0.0002

Data Index: 251090 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.1059. Min Act: -0.0002

Data Index: 574937 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1253990 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1280904 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0889. Min Act: -0.0002

Data Index: 812253 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0866. Min Act: -0.0002

Data Index: 314131 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0857. Min Act: -0.0002

Data Index: 516467 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0890. Min Act: -0.0002

Data Index: 88861 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0819. Min Act: -0.0002

Data Index: 451735 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0834. Min Act: -0.0002

Data Index: 836765 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0850. Min Act: -0.0002

Data Index: 980699 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1335769 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0847. Min Act: -0.0002

Data Index: 307422 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0811. Min Act: -0.0002

Data Index: 588923 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0802. Min Act: -0.0002

Data Index: 884032 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1209643 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1130553 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1292108 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.1207. Min Range: -0.1207

Max Act: 0.0778. Min Act: -0.0002

Data Index: 552841 (C4 (Web Text))

Max Activating Token Index: 837