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

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

Neuron 1680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.7355. Min Act: -0.0000

Data Index: 148022 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.6810. Min Act: -0.0000

Data Index: 1425607 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.5018. Min Act: -0.0000

Data Index: 773648 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.7192. Min Act: -0.0000

Data Index: 1554374 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.3682. Min Act: -0.0000

Data Index: 1452030 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.4195. Min Act: -0.0000

Data Index: 32506 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.4320. Min Act: -0.0000

Data Index: 1416085 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.3811. Min Act: -0.0000

Data Index: 1514655 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.1852. Min Act: -0.0000

Data Index: 443240 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.2427. Min Act: -0.0000

Data Index: 981502 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.2475. Min Act: -0.0000

Data Index: 1543614 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.2396. Min Act: -0.0000

Data Index: 1372572 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.9462. Min Act: -0.0000

Data Index: 252531 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.0079. Min Act: -0.0000

Data Index: 1420848 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.7321. Min Act: -0.0000

Data Index: 972720 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.8264. Min Act: -0.0000

Data Index: 1363052 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.8117. Min Act: -0.0000

Data Index: 1388425 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 3.7355. Min Range: -3.7355

Max Act: 3.0863. Min Act: -0.0000

Data Index: 602136 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.7779. Min Act: -0.0000

Data Index: 1306565 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.7355. Min Range: -3.7355

Max Act: 2.9031. Min Act: -0.0000

Data Index: 684010 (C4 (Web Text))

Max Activating Token Index: 77