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

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

Neuron 1936 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4479. Min Act: 0.0000

Data Index: 654250 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1068113 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3942. Min Act: -0.0001

Data Index: 129491 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3928. Min Act: -0.0000

Data Index: 314270 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1305748 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3662. Min Act: -0.0001

Data Index: 511346 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3620. Min Act: -0.0000

Data Index: 143559 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3790. Min Act: -0.0001

Data Index: 793499 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3714. Min Act: -0.0000

Data Index: 242788 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1347392 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3598. Min Act: -0.0000

Data Index: 326187 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3493. Min Act: -0.0000

Data Index: 270975 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3463. Min Act: -0.0001

Data Index: 344032 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1259708 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3573. Min Act: -0.0000

Data Index: 615354 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3285. Min Act: -0.0000

Data Index: 3969 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3378. Min Act: -0.0000

Data Index: 810990 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1248180 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3441. Min Act: -0.0000

Data Index: 520424 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.4479. Min Range: -0.4479

Max Act: 0.3334. Min Act: -0.0000

Data Index: 660267 (C4 (Web Text))

Max Activating Token Index: 39