Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 462 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0003

Data Index: 1620448 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1273. Min Act: -0.0003

Data Index: 1595659 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1037468 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1007. Min Act: -0.0003

Data Index: 534100 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0982. Min Act: -0.0003

Data Index: 360661 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0883. Min Act: -0.0003

Data Index: 296147 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0809. Min Act: -0.0003

Data Index: 63993 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0963. Min Act: -0.0003

Data Index: 30296 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1504280 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1281492 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0786. Min Act: -0.0003

Data Index: 627254 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0221. Min Act: -0.0003

Data Index: 359275 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0825. Min Act: -0.0003

Data Index: 785717 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1385715 (Python Code)

Max Activating Token Index: 222

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0787. Min Act: -0.0003

Data Index: 1533839 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1610130 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0090. Min Act: -0.0003

Data Index: 1159408 (C4 (Web Text))

Max Activating Token Index: 0

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.0553. Min Act: -0.0003

Data Index: 27370 (C4 (Web Text))

Max Activating Token Index: 842