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

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

Neuron 2684 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.8535. Min Act: -0.0000

Data Index: 452260 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1146397 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.7945. Min Act: -0.0000

Data Index: 572033 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.7652. Min Act: -0.0000

Data Index: 139958 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1011696 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1150765 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6537. Min Act: -0.0000

Data Index: 810070 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6173. Min Act: -0.0000

Data Index: 944090 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6762. Min Act: -0.0000

Data Index: 992577 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6755. Min Act: -0.0000

Data Index: 396573 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1174870 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1122814 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5780. Min Act: -0.0000

Data Index: 195331 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1136682 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5596. Min Act: -0.0000

Data Index: 682972 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5421. Min Act: -0.0000

Data Index: 163629 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5546. Min Act: -0.0000

Data Index: 87552 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5483. Min Act: -0.0000

Data Index: 127087 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.6230. Min Act: -0.0000

Data Index: 118068 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1085963 (C4 (Web Text))

Max Activating Token Index: 114