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

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

Neuron 2846 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.3026. Min Act: -0.0000

Data Index: 1072656 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 2.3026. Min Range: -2.3026

Max Act: 2.1275. Min Act: -0.0000

Data Index: 1630201 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8106. Min Act: -0.0000

Data Index: 673082 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.6864. Min Act: -0.0000

Data Index: 652344 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.7731. Min Act: -0.0000

Data Index: 43757 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.4673. Min Act: -0.0000

Data Index: 637036 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.6873. Min Act: -0.0000

Data Index: 1483276 (Python Code)

Max Activating Token Index: 955

Text #7

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.7415. Min Act: -0.0000

Data Index: 643861 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.8267. Min Act: -0.0000

Data Index: 586364 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.6614. Min Act: -0.0000

Data Index: 21470 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1611198 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5505. Min Act: -0.0000

Data Index: 135861 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.4625. Min Act: -0.0000

Data Index: 526844 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5499. Min Act: 0.0000

Data Index: 841723 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5310. Min Act: -0.0000

Data Index: 35552 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5949. Min Act: -0.0000

Data Index: 941938 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5102. Min Act: -0.0000

Data Index: 346615 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1178923 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.5933. Min Act: -0.0000

Data Index: 1652860 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 2.3026. Min Range: -2.3026

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1319864 (C4 (Web Text))

Max Activating Token Index: 237