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

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

Neuron 3247 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.9360. Min Act: -0.0000

Data Index: 108031 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.6851. Min Act: -0.0000

Data Index: 1527177 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.8056. Min Act: -0.0000

Data Index: 323281 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.0229. Min Range: -2.0229

Max Act: 2.0229. Min Act: -0.0000

Data Index: 1467385 (Python Code)

Max Activating Token Index: 125

Text #4

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.6747. Min Act: -0.0000

Data Index: 1204207 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.7142. Min Act: -0.0001

Data Index: 262234 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.7183. Min Act: -0.0000

Data Index: 66903 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1330776 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.5857. Min Act: -0.0000

Data Index: 1472339 (Python Code)

Max Activating Token Index: 305

Text #9

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1490637 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.4438. Min Act: -0.0000

Data Index: 293403 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.5040. Min Act: -0.0000

Data Index: 454810 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.4786. Min Act: -0.0000

Data Index: 366444 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1459155 (Python Code)

Max Activating Token Index: 543

Text #14

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.5455. Min Act: -0.0000

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.5797. Min Act: -0.0000

Data Index: 33498 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1506537 (Python Code)

Max Activating Token Index: 533

Text #17

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.4323. Min Act: -0.0000

Data Index: 896901 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.3452. Min Act: -0.0000

Data Index: 999831 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 2.0229. Min Range: -2.0229

Max Act: 1.1861. Min Act: -0.0000

Data Index: 452524 (C4 (Web Text))

Max Activating Token Index: 946