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

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

Neuron 1326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1053399 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8408. Min Act: -0.0000

Data Index: 784522 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7912. Min Act: -0.0000

Data Index: 317225 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8110. Min Act: -0.0000

Data Index: 802110 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1169655 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8094. Min Act: -0.0000

Data Index: 748877 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8043. Min Act: -0.0000

Data Index: 557709 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1349003 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1334969 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1106374 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7675. Min Act: -0.0000

Data Index: 871403 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.8434. Min Act: -0.0000

Data Index: 832209 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1194256 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1110600 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7846. Min Act: -0.0000

Data Index: 240671 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7766. Min Act: -0.0000

Data Index: 481314 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7817. Min Act: -0.0000

Data Index: 280840 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7732. Min Act: -0.0000

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1068228 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.8849. Min Range: -0.8849

Max Act: 0.7532. Min Act: -0.0000

Data Index: 919494 (C4 (Web Text))

Max Activating Token Index: 704