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

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

Neuron 4866 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1584417 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1607774 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1381644 (Python Code)

Max Activating Token Index: 957

Text #3

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1618024 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5836. Min Act: -0.0000

Data Index: 191734 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5284. Min Act: -0.0000

Data Index: 636804 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1540061 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1509299 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1281460 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1478895 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1447210 (Python Code)

Max Activating Token Index: 908

Text #11

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4905. Min Act: 0.0000

Data Index: 1636370 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1588428 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1400872 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1553763 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1374931 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1363350 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1459758 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4561. Min Act: -0.0000

Data Index: 418335 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.7461. Min Range: -0.7461

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1426693 (Python Code)

Max Activating Token Index: 861