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

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

Neuron 4973 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1499104 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1448885 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.2576. Min Act: -0.0000

Data Index: 1366992 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1484113 (Python Code)

Max Activating Token Index: 165

Text #4

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1608301 (Python Code)

Max Activating Token Index: 498

Text #5

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1435280 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.2060. Min Act: -0.0000

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1413561 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1655577 (Python Code)

Max Activating Token Index: 222

Text #9

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1580388 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1626067 (Python Code)

Max Activating Token Index: 288

Text #11

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1385350 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0090. Min Act: -0.0000

Data Index: 36474 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0086. Min Act: -0.0000

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 1.3483. Min Range: -1.3483

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1532807 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1437193 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9749. Min Act: -0.0000

Data Index: 870412 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9209. Min Act: -0.0000

Data Index: 659845 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1436751 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 1.3483. Min Range: -1.3483

Max Act: 0.9749. Min Act: -0.0000

Data Index: 40032 (C4 (Web Text))

Max Activating Token Index: 259