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

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

Neuron 576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.6810. Min Act: -0.0000

Data Index: 1115055 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.7718. Min Act: -0.0000

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1180 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.5867. Min Act: -0.0000

Data Index: 764653 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1261320 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.6027. Min Act: -0.0000

Data Index: 934318 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3300. Min Act: -0.0000

Data Index: 1342377 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.4535. Min Act: -0.0000

Data Index: 280133 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.4238. Min Act: -0.0000

Data Index: 1187878 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.0353. Min Act: -0.0000

Data Index: 694317 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3326. Min Act: -0.0000

Data Index: 171176 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1378432 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.2929. Min Act: -0.0000

Data Index: 183193 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.4573. Min Act: -0.0000

Data Index: 912432 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.2856. Min Act: -0.0000

Data Index: 899146 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1114782 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.2772. Min Act: -0.0000

Data Index: 450671 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3349. Min Act: -0.0000

Data Index: 729189 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1143076 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.7718. Min Range: -1.7718

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1226180 (C4 (Web Text))

Max Activating Token Index: 419