Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5157. Min Range: -2.5157

Max Act: 2.5157. Min Act: -0.0000

Data Index: 873504 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 2.5157. Min Range: -2.5157

Max Act: 2.2138. Min Act: -0.0000

Data Index: 803397 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1223743 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7514. Min Act: -0.0000

Data Index: 893859 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7700. Min Act: -0.0000

Data Index: 585606 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.8833. Min Act: -0.0000

Data Index: 235477 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.8335. Min Act: -0.0000

Data Index: 848560 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7044. Min Act: -0.0000

Data Index: 353463 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7068. Min Act: -0.0000

Data Index: 46722 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6984. Min Act: -0.0000

Data Index: 6182 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7930. Min Act: -0.0000

Data Index: 82173 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7534. Min Act: -0.0000

Data Index: 891147 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6223. Min Act: -0.0000

Data Index: 530864 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1035476 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.7359. Min Act: -0.0000

Data Index: 399054 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1021170 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.5329. Min Act: -0.0000

Data Index: 507282 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6128. Min Act: -0.0000

Data Index: 686929 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.4355. Min Act: -0.0000

Data Index: 900991 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.5157. Min Range: -2.5157

Max Act: 1.6007. Min Act: -0.0000

Data Index: 346919 (C4 (Web Text))

Max Activating Token Index: 320