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

Dataset: The Pile

Neuron 4602 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: 1.7302. Min Range: -1.7302

Max Act: 1.7302. Min Act: -0.0000

Data Index: 1422992 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6567. Min Act: -0.0000

Data Index: 481968 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6581. Min Act: -0.0000

Data Index: 1499764 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1780992 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6369. Min Act: -0.0000

Data Index: 1680342 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5470. Min Act: -0.0000

Data Index: 1700280 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1013544 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4635. Min Act: -0.0000

Data Index: 1980508 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1639314 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1319524 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1497608 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4909. Min Act: -0.0000

Data Index: 350766 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6513. Min Act: -0.0000

Data Index: 739388 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1083928 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1690441 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.3311. Min Act: -0.0000

Data Index: 30236 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5524. Min Act: -0.0000

Data Index: 1499202 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1330094 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1893153 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1081627 (The Pile)

Max Activating Token Index: 323