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

Dataset: The Pile

Neuron 2833 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: 3.6223. Min Range: -3.6223

Max Act: 3.5535. Min Act: -0.0000

Data Index: 788126 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.6223. Min Act: -0.0000

Data Index: 1117047 (The Pile)

Max Activating Token Index: 134

Text #2

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.3248. Min Act: -0.0000

Data Index: 1484426 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8585. Min Act: -0.0000

Data Index: 231476 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.3573. Min Act: -0.0000

Data Index: 614431 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.1964. Min Act: -0.0000

Data Index: 1913238 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.1720. Min Act: -0.0000

Data Index: 1875326 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.1513. Min Act: -0.0000

Data Index: 1569321 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.1196. Min Act: -0.0000

Data Index: 1438216 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.1015. Min Act: -0.0000

Data Index: 1455739 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8767. Min Act: -0.0000

Data Index: 679995 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.2758. Min Act: -0.0000

Data Index: 1658976 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 3.6223. Min Range: -3.6223

Max Act: 3.0987. Min Act: -0.0000

Data Index: 1759309 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.7803. Min Act: -0.0000

Data Index: 1934433 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8591. Min Act: -0.0000

Data Index: 1003323 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1560222 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.7122. Min Act: -0.0000

Data Index: 939570 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8301. Min Act: -0.0000

Data Index: 1164747 (The Pile)

Max Activating Token Index: 796

Text #18

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.8399. Min Act: -0.0000

Data Index: 1524561 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 3.6223. Min Range: -3.6223

Max Act: 2.7122. Min Act: -0.0000

Data Index: 319966 (The Pile)

Max Activating Token Index: 619