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

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

Neuron 728 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.6599. Min Act: -0.0000

Data Index: 87644 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.2326. Min Act: -0.0000

Data Index: 396020 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.1954. Min Act: -0.0000

Data Index: 1301281 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.0987. Min Act: -0.0000

Data Index: 840817 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.9514. Min Act: -0.0000

Data Index: 229212 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.0491. Min Act: -0.0000

Data Index: 701649 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 2.6599. Min Range: -2.6599

Max Act: 2.0111. Min Act: -0.0000

Data Index: 876366 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.8835. Min Act: -0.0000

Data Index: 763431 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.9959. Min Act: -0.0000

Data Index: 290087 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1159460 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.7991. Min Act: -0.0000

Data Index: 973230 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.8019. Min Act: -0.0000

Data Index: 1220019 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.8263. Min Act: -0.0000

Data Index: 169152 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.7706. Min Act: -0.0000

Data Index: 125491 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.6735. Min Act: -0.0000

Data Index: 1539308 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.6839. Min Act: -0.0000

Data Index: 400290 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1151436 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.8501. Min Act: -0.0000

Data Index: 1640423 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.6378. Min Act: -0.0000

Data Index: 195168 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.6599. Min Range: -2.6599

Max Act: 1.7439. Min Act: -0.0000

Data Index: 294840 (C4 (Web Text))

Max Activating Token Index: 244