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

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

Neuron 1789 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: 0.9868. Min Range: -0.9868

Max Act: 0.9868. Min Act: -0.0000

Data Index: 818546 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8000. Min Act: -0.0000

Data Index: 690151 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.8165. Min Act: -0.0000

Data Index: 140724 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7261. Min Act: -0.0000

Data Index: 883281 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7935. Min Act: -0.0000

Data Index: 843070 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6900. Min Act: -0.0000

Data Index: 16461 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6487. Min Act: -0.0000

Data Index: 909531 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7178. Min Act: -0.0000

Data Index: 248936 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1342722 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6857. Min Act: -0.0000

Data Index: 843378 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6892. Min Act: -0.0000

Data Index: 524002 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1283219 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6240. Min Act: -0.0000

Data Index: 561782 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.5982. Min Act: -0.0000

Data Index: 555266 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6163. Min Act: -0.0000

Data Index: 137146 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6145. Min Act: -0.0000

Data Index: 40447 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6528. Min Act: -0.0000

Data Index: 806315 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.5969. Min Act: -0.0000

Data Index: 607024 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1196025 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.9868. Min Range: -0.9868

Max Act: 0.5866. Min Act: -0.0000

Data Index: 929079 (C4 (Web Text))

Max Activating Token Index: 493