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

Dataset: The Pile

Neuron 3518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.6421. Min Act: -0.0000

Data Index: 839084 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1199536 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1249495 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.0814. Min Act: -0.0000

Data Index: 701964 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1580166 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1373233 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1236407 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1918123 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.6421. Min Range: -1.6421

Max Act: 1.0249. Min Act: -0.0000

Data Index: 783449 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1749667 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9198. Min Act: -0.0000

Data Index: 929644 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.9046. Min Act: -0.0000

Data Index: 911404 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1973073 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8345. Min Act: -0.0000

Data Index: 845698 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1346527 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8308. Min Act: -0.0000

Data Index: 339938 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.7731. Min Act: -0.0000

Data Index: 357580 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1827605 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1097084 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.6421. Min Range: -1.6421

Max Act: 0.8103. Min Act: -0.0000

Data Index: 223956 (The Pile)

Max Activating Token Index: 85