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

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

Neuron 4426 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1397388 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1452045 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.3470. Min Act: -0.0000

Data Index: 1422678 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.2171. Min Act: -0.0000

Data Index: 1627180 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.0906. Min Act: -0.0000

Data Index: 1649511 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1559314 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1321075 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1389869 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1619412 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1409799 (Python Code)

Max Activating Token Index: 849

Text #10

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1382061 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 2.7169. Min Range: -2.7169

Max Act: 2.1001. Min Act: -0.0000

Data Index: 1551576 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.8736. Min Act: -0.0000

Data Index: 882332 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.7509. Min Act: -0.0000

Data Index: 1591093 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.8620. Min Act: -0.0000

Data Index: 1562216 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.8393. Min Act: -0.0000

Data Index: 1631959 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.6853. Min Act: -0.0000

Data Index: 560921 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.7648. Min Act: -0.0000

Data Index: 801474 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.8650. Min Act: -0.0000

Data Index: 1340694 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 2.7169. Min Range: -2.7169

Max Act: 1.8692. Min Act: -0.0000

Data Index: 1362973 (Python Code)

Max Activating Token Index: 906