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

Dataset: The Pile

Neuron 4314 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1048231 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3121. Min Act: -0.0000

Data Index: 100514 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3036. Min Act: -0.0000

Data Index: 368102 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2965. Min Act: -0.0000

Data Index: 726700 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1443910 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2939. Min Act: -0.0000

Data Index: 283321 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2950. Min Act: -0.0000

Data Index: 745482 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1754953 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2302. Min Act: -0.0000

Data Index: 399277 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2510. Min Act: -0.0000

Data Index: 387611 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2124. Min Act: -0.0000

Data Index: 645534 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2262. Min Act: -0.0000

Data Index: 930885 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1083934 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1967393 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2147. Min Act: -0.0000

Data Index: 613038 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2300. Min Act: -0.0000

Data Index: 82449 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1632175 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1080745 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2217. Min Act: -0.0000

Data Index: 85661 (The Pile)

Max Activating Token Index: 622

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.1923. Min Act: -0.0000

Data Index: 725237 (The Pile)

Max Activating Token Index: 967