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

Dataset: The Pile

Neuron 3857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1658100 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1819713 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3458. Min Act: -0.0000

Data Index: 869735 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1036854 (The Pile)

Max Activating Token Index: 316

Text #4

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3318. Min Act: -0.0000

Data Index: 331877 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3344. Min Act: -0.0000

Data Index: 540480 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1883412 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1622444 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3374. Min Act: -0.0000

Data Index: 457752 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3077. Min Act: -0.0000

Data Index: 152760 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3323. Min Act: -0.0000

Data Index: 898446 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1877028 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1415306 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1319308 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1441983 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2871. Min Act: -0.0000

Data Index: 217245 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3066. Min Act: -0.0000

Data Index: 493998 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2975. Min Act: -0.0000

Data Index: 156833 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1488898 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1388934 (The Pile)

Max Activating Token Index: 485