Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2431 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0574. Min Range: -1.0574

Max Act: 1.0574. Min Act: -0.0000

Data Index: 681981 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9745. Min Act: -0.0000

Data Index: 794834 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9152. Min Act: -0.0000

Data Index: 43328 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1835017 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1623352 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8959. Min Act: -0.0000

Data Index: 241438 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8709. Min Act: -0.0000

Data Index: 588453 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1691812 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8070. Min Act: -0.0000

Data Index: 154387 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8767. Min Act: -0.0000

Data Index: 645326 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8376. Min Act: -0.0000

Data Index: 599078 (The Pile)

Max Activating Token Index: 428

Text #11

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8242. Min Act: -0.0000

Data Index: 233830 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1866394 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8544. Min Act: -0.0000

Data Index: 487734 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8257. Min Act: -0.0000

Data Index: 89633 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8087. Min Act: -0.0000

Data Index: 705313 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1153364 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1423380 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1973365 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1105324 (The Pile)

Max Activating Token Index: 21