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

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

Neuron 1353 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.8371. Min Act: -0.0001

Data Index: 958746 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.3706. Min Act: -0.0000

Data Index: 868688 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.4243. Min Act: -0.0000

Data Index: 272088 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.2398. Min Act: -0.0001

Data Index: 1182442 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.2156. Min Act: -0.0001

Data Index: 24090 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.0377. Min Act: -0.0001

Data Index: 511968 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.3166. Min Act: -0.0001

Data Index: 773295 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.9985. Min Act: -0.0000

Data Index: 789794 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.1247. Min Act: -0.0001

Data Index: 461410 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.9262. Min Act: -0.0001

Data Index: 700573 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.7566. Min Act: -0.0001

Data Index: 1333781 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.5106. Min Act: -0.0000

Data Index: 414792 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.5486. Min Act: -0.0001

Data Index: 1166312 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.8726. Min Act: -0.0001

Data Index: 257572 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.8878. Min Act: -0.0000

Data Index: 796373 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 5.8371. Min Range: -5.8371

Max Act: 5.1760. Min Act: -0.0000

Data Index: 551753 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.8476. Min Act: -0.0001

Data Index: 97798 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.3328. Min Act: -0.0001

Data Index: 1044895 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.6681. Min Act: -0.0001

Data Index: 605385 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 5.8371. Min Range: -5.8371

Max Act: 4.4896. Min Act: -0.0001

Data Index: 1073991 (C4 (Web Text))

Max Activating Token Index: 987