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

Dataset: The Pile

Neuron 3311 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: 3.8342. Min Range: -3.8342

Max Act: 3.6494. Min Act: -0.0000

Data Index: 1455087 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.7130. Min Act: -0.0000

Data Index: 1968497 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.6942. Min Act: -0.0000

Data Index: 1215460 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.6679. Min Act: -0.0000

Data Index: 740789 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.6699. Min Act: -0.0000

Data Index: 985925 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.4696. Min Act: -0.0000

Data Index: 1778603 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.5657. Min Act: -0.0000

Data Index: 1251378 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.5888. Min Act: -0.0000

Data Index: 1216246 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.8342. Min Act: -0.0000

Data Index: 1477688 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.4560. Min Act: -0.0000

Data Index: 1385948 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.5489. Min Act: -0.0000

Data Index: 1172094 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.2342. Min Act: -0.0000

Data Index: 1855819 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.1899. Min Act: -0.0000

Data Index: 840085 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.1554. Min Act: -0.0000

Data Index: 770836 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.1623. Min Act: -0.0000

Data Index: 582426 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.2765. Min Act: -0.0000

Data Index: 347387 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.1166. Min Act: -0.0000

Data Index: 141663 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.2371. Min Act: -0.0000

Data Index: 1870479 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.0747. Min Act: -0.0000

Data Index: 1053724 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 3.8342. Min Range: -3.8342

Max Act: 3.3397. Min Act: -0.0000

Data Index: 1215684 (The Pile)

Max Activating Token Index: 328