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

Dataset: The Pile

Neuron 3008 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: 0.5668. Min Range: -0.5668

Max Act: 0.5554. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5668. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5127. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5130. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1679032 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4799. Min Act: -0.0000

Data Index: 13979 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4777. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5221. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1888153 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3643. Min Act: -0.0000

Data Index: 630430 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3540. Min Act: -0.0000

Data Index: 598881 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1798751 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.2194. Min Act: -0.0000

Data Index: 232363 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.2230. Min Act: -0.0000

Data Index: 625245 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1920959 (The Pile)

Max Activating Token Index: 887

Text #19

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.2112. Min Act: -0.0000

Data Index: 299630 (The Pile)

Max Activating Token Index: 483