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

Dataset: The Pile

Neuron 4565 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: 5.8033. Min Range: -5.8033

Max Act: 5.6417. Min Act: -0.0000

Data Index: 1923824 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 5.8033. Min Range: -5.8033

Max Act: 5.8033. Min Act: -0.0000

Data Index: 207457 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 5.8033. Min Range: -5.8033

Max Act: 5.5732. Min Act: -0.0000

Data Index: 469325 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 5.8033. Min Range: -5.8033

Max Act: 4.5249. Min Act: -0.0000

Data Index: 1097087 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 5.8033. Min Range: -5.8033

Max Act: 4.5317. Min Act: -0.0000

Data Index: 139373 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 5.8033. Min Range: -5.8033

Max Act: 4.3020. Min Act: -0.0000

Data Index: 921223 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 5.8033. Min Range: -5.8033

Max Act: 4.3760. Min Act: -0.0000

Data Index: 1292015 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.9105. Min Act: -0.0000

Data Index: 726236 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.8907. Min Act: -0.0000

Data Index: 487207 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.6523. Min Act: -0.0000

Data Index: 924085 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.8253. Min Act: -0.0000

Data Index: 58965 (The Pile)

Max Activating Token Index: 848

Text #11

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.8866. Min Act: -0.0000

Data Index: 891559 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.7040. Min Act: -0.0000

Data Index: 886020 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.4941. Min Act: -0.0000

Data Index: 930131 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.4332. Min Act: -0.0000

Data Index: 64831 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.2535. Min Act: -0.0000

Data Index: 1194267 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.2177. Min Act: -0.0000

Data Index: 176966 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.3536. Min Act: -0.0000

Data Index: 975882 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.2869. Min Act: -0.0000

Data Index: 1099339 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 5.8033. Min Range: -5.8033

Max Act: 3.2543. Min Act: -0.0000

Data Index: 677859 (The Pile)

Max Activating Token Index: 433