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

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

Neuron 3783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.7373. Min Act: -0.0000

Data Index: 70135 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.7301. Min Act: -0.0000

Data Index: 61563 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6725. Min Act: 0.0000

Data Index: 918653 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6816. Min Act: -0.0000

Data Index: 128400 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6564. Min Act: -0.0000

Data Index: 7993 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6464. Min Act: -0.0000

Data Index: 446617 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6420. Min Act: 0.0000

Data Index: 885624 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6348. Min Act: -0.0000

Data Index: 940797 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6325. Min Act: -0.0000

Data Index: 826620 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5887. Min Act: -0.0000

Data Index: 246332 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6288. Min Act: 0.0000

Data Index: 1002344 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1037212 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6264. Min Act: -0.0000

Data Index: 617388 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1025654 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5809. Min Act: 0.0000

Data Index: 503973 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1097618 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5975. Min Act: -0.0000

Data Index: 397235 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5728. Min Act: -0.0000

Data Index: 591048 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5828. Min Act: -0.0000

Data Index: 220602 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5728. Min Act: -0.0000

Data Index: 837255 (C4 (Web Text))

Max Activating Token Index: 125