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

Dataset: The Pile

Neuron 4574 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1770335 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1737461 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1280287 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5273. Min Act: -0.0000

Data Index: 47349 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5180. Min Act: -0.0000

Data Index: 77501 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1899156 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1635179 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1844799 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5357. Min Act: -0.0000

Data Index: 602282 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1910579 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5297. Min Act: -0.0000

Data Index: 802592 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4854. Min Act: -0.0000

Data Index: 46214 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1620095 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1907513 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5099. Min Act: -0.0000

Data Index: 717051 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1921540 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1843376 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1839919 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1841844 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1553210 (The Pile)

Max Activating Token Index: 770