Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2240. Min Act: -0.0001

Data Index: 162825 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1131533 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1198257 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1338040 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1954. Min Act: -0.0000

Data Index: 402472 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1860. Min Act: -0.0000

Data Index: 35564 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1527403 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1880. Min Act: -0.0001

Data Index: 44648 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1047487 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1274659 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1095881 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1654895 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1370424 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1713. Min Act: -0.0000

Data Index: 556497 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1727. Min Act: -0.0000

Data Index: 857642 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1264495 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1445515 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1704. Min Act: -0.0000

Data Index: 280551 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1697. Min Act: -0.0001

Data Index: 600031 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1100402 (C4 (Web Text))

Max Activating Token Index: 682