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

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

Neuron 1137 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.6069. Min Act: -0.0000

Data Index: 793703 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4178. Min Act: -0.0000

Data Index: 291200 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1342384 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3805. Min Act: -0.0000

Data Index: 107016 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1168023 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2730. Min Act: -0.0000

Data Index: 949797 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3676. Min Act: -0.0000

Data Index: 517782 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1193912 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3340. Min Act: -0.0000

Data Index: 602830 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2445. Min Act: -0.0000

Data Index: 61822 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3172. Min Act: -0.0000

Data Index: 847344 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1990. Min Act: -0.0000

Data Index: 141899 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2496. Min Act: -0.0000

Data Index: 314373 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2499. Min Act: -0.0000

Data Index: 800591 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2346. Min Act: -0.0000

Data Index: 851245 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.3254. Min Act: -0.0000

Data Index: 117620 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2593. Min Act: -0.0000

Data Index: 493427 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2335. Min Act: -0.0000

Data Index: 974251 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.2528. Min Act: -0.0000

Data Index: 282344 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.6069. Min Range: -1.6069

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1075629 (C4 (Web Text))

Max Activating Token Index: 150