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

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

Neuron 2292 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.4236. Min Act: -0.0000

Data Index: 483601 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1012499 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3280. Min Act: -0.0000

Data Index: 322560 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3161. Min Act: -0.0000

Data Index: 812853 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3142. Min Act: -0.0000

Data Index: 15503 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1044736 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3336. Min Act: -0.0000

Data Index: 268789 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3173. Min Act: -0.0000

Data Index: 185461 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3149. Min Act: -0.0000

Data Index: 598700 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1334170 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1131256 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1036296 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1280133 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2915. Min Act: -0.0000

Data Index: 792534 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2833. Min Act: -0.0000

Data Index: 608436 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2853. Min Act: -0.0000

Data Index: 367769 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2786. Min Act: -0.0000

Data Index: 682938 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2623. Min Act: -0.0000

Data Index: 868406 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2709. Min Act: -0.0000

Data Index: 59102 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.4236. Min Range: -0.4236

Max Act: 0.2506. Min Act: -0.0000

Data Index: 732949 (C4 (Web Text))

Max Activating Token Index: 874