Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3788 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1366416 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1365547 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1378258 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1371087 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1366342 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1376599 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1375424 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1361986 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1364003 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1376884 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1370771 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1373135 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1361553 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1372222 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1367973 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1367331 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1367305 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1366710 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1364190 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1371300 (Python Code)

Max Activating Token Index: 1