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

Dataset: The Pile

Neuron 4505 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: 0.6914. Min Range: -0.6914

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1598080 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1885803 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1727093 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1152591 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1092741 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1448572 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4706. Min Act: -0.0000

Data Index: 543854 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1902719 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3941. Min Act: -0.0000

Data Index: 116482 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3769. Min Act: -0.0000

Data Index: 155175 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3870. Min Act: -0.0000

Data Index: 411269 (The Pile)

Max Activating Token Index: 205

Text #11

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3696. Min Act: -0.0000

Data Index: 956236 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3641. Min Act: -0.0000

Data Index: 219600 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1308119 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3568. Min Act: -0.0000

Data Index: 621520 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1641944 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3256. Min Act: -0.0000

Data Index: 439916 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3353. Min Act: -0.0000

Data Index: 629347 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3232. Min Act: -0.0000

Data Index: 4744 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.6914. Min Range: -0.6914

Max Act: 0.3061. Min Act: -0.0000

Data Index: 860097 (The Pile)

Max Activating Token Index: 194