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

Dataset: The Pile

Neuron 4103 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: 0.9059. Min Range: -0.9059

Max Act: 0.9059. Min Act: -0.0000

Data Index: 851853 (The Pile)

Max Activating Token Index: 401

Text #1

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8141. Min Act: -0.0000

Data Index: 689167 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8229. Min Act: -0.0000

Data Index: 360678 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1795382 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1112833 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1869368 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7730. Min Act: -0.0000

Data Index: 123472 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7229. Min Act: -0.0000

Data Index: 728696 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1807996 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7750. Min Act: -0.0000

Data Index: 864539 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6933. Min Act: -0.0000

Data Index: 396587 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1557438 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1509455 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7215. Min Act: -0.0000

Data Index: 286618 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1381267 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1837055 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6216. Min Act: -0.0000

Data Index: 517405 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6849. Min Act: -0.0000

Data Index: 790840 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1771436 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.9059. Min Range: -0.9059

Max Act: 0.6404. Min Act: -0.0000

Data Index: 591205 (The Pile)

Max Activating Token Index: 958