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

Dataset: The Pile

Neuron 2916 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1878338 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3953. Min Act: -0.0000

Data Index: 168457 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4597. Min Act: -0.0000

Data Index: 37038 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1877289 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1607361 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1750306 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1390652 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1610575 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3461. Min Act: -0.0000

Data Index: 626251 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3278. Min Act: -0.0000

Data Index: 994978 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1238861 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3461. Min Act: -0.0000

Data Index: 483726 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1266502 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1136773 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.2856. Min Act: -0.0000

Data Index: 346062 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3099. Min Act: -0.0000

Data Index: 474887 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1084868 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3411. Min Act: -0.0000

Data Index: 660875 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1306530 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.4597. Min Range: -0.4597

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1464831 (The Pile)

Max Activating Token Index: 929