Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1195 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1204382 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.4896. Min Act: -0.0000

Data Index: 711985 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1575856 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3874. Min Act: -0.0000

Data Index: 66721 (The Pile)

Max Activating Token Index: 246

Text #4

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3720. Min Act: -0.0000

Data Index: 762421 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1577728 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1575819 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3950. Min Act: -0.0000

Data Index: 364085 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1577868 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1292705 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3290. Min Act: -0.0000

Data Index: 59404 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3772. Min Act: -0.0000

Data Index: 911178 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3523. Min Act: -0.0000

Data Index: 725831 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1029921 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1269244 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1080291 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1981517 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1613048 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1708407 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.4896. Min Range: -0.4896

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1397250 (The Pile)

Max Activating Token Index: 900