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

Dataset: The Pile

Neuron 4028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8888. Min Act: -0.0000

Data Index: 418295 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.9007. Min Act: -0.0000

Data Index: 239261 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8500. Min Act: -0.0000

Data Index: 784274 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1915461 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1124981 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1915453 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6868. Min Act: -0.0000

Data Index: 533668 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1258680 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7195. Min Act: -0.0000

Data Index: 705034 (The Pile)

Max Activating Token Index: 846

Text #9

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7313. Min Act: -0.0000

Data Index: 456142 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6901. Min Act: -0.0000

Data Index: 538830 (The Pile)

Max Activating Token Index: 445

Text #11

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7259. Min Act: -0.0000

Data Index: 340238 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6954. Min Act: -0.0000

Data Index: 564419 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5988. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5849. Min Act: -0.0000

Data Index: 850492 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1273233 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1133401 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5403. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1643102 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1388529 (The Pile)

Max Activating Token Index: 290