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

Dataset: The Pile

Neuron 4218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5245. Min Act: -0.0000

Data Index: 602607 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.6237. Min Act: -0.0000

Data Index: 674223 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.6269. Min Act: -0.0000

Data Index: 1514400 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.8295. Min Act: -0.0000

Data Index: 1352820 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5609. Min Act: -0.0000

Data Index: 995954 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5374. Min Act: -0.0000

Data Index: 570909 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4858. Min Act: -0.0000

Data Index: 1771344 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3797. Min Act: -0.0000

Data Index: 817881 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1924535 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1171212 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1764738 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4668. Min Act: -0.0000

Data Index: 926966 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1945874 (The Pile)

Max Activating Token Index: 410

Text #13

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1491018 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1029561 (The Pile)

Max Activating Token Index: 353

Text #15

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.4303. Min Act: -0.0000

Data Index: 989784 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3716. Min Act: -0.0000

Data Index: 249536 (The Pile)

Max Activating Token Index: 745

Text #17

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3966. Min Act: -0.0000

Data Index: 888300 (The Pile)

Max Activating Token Index: 533

Text #18

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1583653 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.8295. Min Range: -1.8295

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1571709 (The Pile)

Max Activating Token Index: 715