Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.8026. Min Act: -0.0000

Data Index: 268517 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.7526. Min Act: -0.0000

Data Index: 390257 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1826916 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1929492 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.7978. Min Act: -0.0000

Data Index: 897274 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6521. Min Act: -0.0000

Data Index: 772636 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6394. Min Act: 0.0000

Data Index: 744351 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1822997 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1593026 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1168585 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6597. Min Act: -0.0000

Data Index: 139450 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6042. Min Act: -0.0000

Data Index: 85501 (The Pile)

Max Activating Token Index: 414

Text #12

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1892042 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6739. Min Act: -0.0000

Data Index: 521255 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6330. Min Act: -0.0000

Data Index: 878422 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1892794 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6051. Min Act: -0.0000

Data Index: 983499 (The Pile)

Max Activating Token Index: 318

Text #17

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1999991 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1829702 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.8026. Min Range: -0.8026

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1498604 (The Pile)

Max Activating Token Index: 768