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

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

Neuron 5325 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1415134 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.1406. Min Act: -0.0000

Data Index: 208257 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.0727. Min Act: -0.0000

Data Index: 909059 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9906. Min Act: -0.0000

Data Index: 494837 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.1036. Min Act: -0.0000

Data Index: 91052 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1607280 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1407712 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1562244 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.0052. Min Act: -0.0000

Data Index: 609627 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9509. Min Act: -0.0000

Data Index: 426194 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1593441 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1055600 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1577388 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8998. Min Act: -0.0000

Data Index: 538450 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1528322 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1450347 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1418421 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1580267 (Python Code)

Max Activating Token Index: 809

Text #18

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1632489 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1561994 (Python Code)

Max Activating Token Index: 411