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

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

Neuron 745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1186351 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.4446. Min Act: -0.0000

Data Index: 423402 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.5220. Min Act: -0.0000

Data Index: 465312 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.3927. Min Act: 0.0002

Data Index: 753263 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.4555. Min Act: -0.0000

Data Index: 678263 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.4349. Min Act: 0.0001

Data Index: 850317 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.2909. Min Act: 0.0001

Data Index: 339081 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1957. Min Act: 0.0002

Data Index: 205745 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.2475. Min Act: -0.0000

Data Index: 790712 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1093112 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.2405. Min Act: -0.0000

Data Index: 242029 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1939. Min Act: -0.0000

Data Index: 906566 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.2381. Min Act: 0.0000

Data Index: 998639 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1169662 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1405. Min Act: -0.0000

Data Index: 443260 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1376. Min Act: -0.0000

Data Index: 569861 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1997. Min Act: -0.0000

Data Index: 103603 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1152. Min Act: 0.0002

Data Index: 899859 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.0887. Min Act: 0.0000

Data Index: 693869 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.5411. Min Range: -1.5411

Max Act: 1.1572. Min Act: -0.0000

Data Index: 942644 (C4 (Web Text))

Max Activating Token Index: 994