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

Dataset: The Pile

Neuron 4036 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: 1.4882. Min Range: -1.4882

Max Act: 1.4882. Min Act: -0.0000

Data Index: 1114770 (The Pile)

Max Activating Token Index: 311

Text #1

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.4269. Min Act: -0.0000

Data Index: 180639 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2839. Min Act: -0.0000

Data Index: 484453 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3301. Min Act: -0.0000

Data Index: 174233 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1414 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1053829 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1971219 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.3020. Min Act: -0.0000

Data Index: 1610896 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2504. Min Act: -0.0000

Data Index: 88465 (The Pile)

Max Activating Token Index: 164

Text #9

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1997. Min Act: -0.0000

Data Index: 281187 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1483. Min Act: -0.0000

Data Index: 407138 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.0799. Min Act: -0.0000

Data Index: 324974 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1042020 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1023408 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1839330 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1965105 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1039. Min Act: -0.0000

Data Index: 416 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.1282. Min Act: -0.0000

Data Index: 967341 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1842065 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 1.4882. Min Range: -1.4882

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1464933 (The Pile)

Max Activating Token Index: 402