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

Dataset: The Pile

Neuron 3118 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: 0.6128. Min Range: -0.6128

Max Act: 0.6128. Min Act: -0.0000

Data Index: 481693 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5644. Min Act: -0.0000

Data Index: 346416 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.5230. Min Act: -0.0000

Data Index: 964820 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1289168 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1431611 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1310419 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1032347 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4729. Min Act: -0.0000

Data Index: 777765 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4356. Min Act: -0.0000

Data Index: 31569 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4595. Min Act: -0.0000

Data Index: 519814 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4437. Min Act: -0.0000

Data Index: 542088 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1914349 (The Pile)

Max Activating Token Index: 279

Text #12

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4325. Min Act: 0.0000

Data Index: 215282 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4638. Min Act: -0.0000

Data Index: 191447 (The Pile)

Max Activating Token Index: 27

Text #14

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4122. Min Act: -0.0000

Data Index: 954320 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4322. Min Act: -0.0000

Data Index: 212294 (The Pile)

Max Activating Token Index: 91

Text #16

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1000937 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.4159. Min Act: -0.0000

Data Index: 301314 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.3961. Min Act: -0.0000

Data Index: 372093 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 0.6128. Min Range: -0.6128

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1431592 (The Pile)

Max Activating Token Index: 117