Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1296 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0528. Min Act: -0.0002

Data Index: 298009 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1184040 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1179059 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0433. Min Act: -0.0001

Data Index: 834081 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0438. Min Act: -0.0001

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0368. Min Act: -0.0001

Data Index: 706498 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0449. Min Act: -0.0001

Data Index: 799597 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0454. Min Act: -0.0001

Data Index: 551966 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0435. Min Act: -0.0001

Data Index: 85900 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1518291 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1062199 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0390. Min Act: -0.0001

Data Index: 396135 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1614400 (Python Code)

Max Activating Token Index: 591

Text #13

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1417757 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0300. Min Act: -0.0001

Data Index: 769681 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0369. Min Act: -0.0002

Data Index: 73337 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0313. Min Act: -0.0001

Data Index: 896478 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1620984 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1442322 (Python Code)

Max Activating Token Index: 677

Text #19

Max Range: 0.0559. Min Range: -0.0559

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1468483 (Python Code)

Max Activating Token Index: 470