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

Dataset: The Pile

Neuron 3580 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: 0.7055. Min Range: -0.7055

Max Act: 0.6810. Min Act: -0.0000

Data Index: 113258 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.7055. Min Act: -0.0000

Data Index: 599895 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1423358 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1377751 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1305269 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6095. Min Act: -0.0000

Data Index: 115625 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6738. Min Act: -0.0000

Data Index: 554210 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5776. Min Act: -0.0000

Data Index: 537173 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6221. Min Act: -0.0000

Data Index: 870034 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6394. Min Act: -0.0000

Data Index: 827035 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1839319 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1135612 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6055. Min Act: -0.0000

Data Index: 491263 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1448825 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1748721 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1735600 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.6450. Min Act: -0.0000

Data Index: 513878 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1111030 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1083896 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.7055. Min Range: -0.7055

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1869547 (The Pile)

Max Activating Token Index: 752