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

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

Neuron 1811 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.1398. Min Act: -0.0000

Data Index: 1043431 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 5.1398. Min Range: -5.1398

Max Act: 5.0728. Min Act: -0.0000

Data Index: 871439 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8608. Min Act: -0.0000

Data Index: 432061 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8683. Min Act: -0.0000

Data Index: 453196 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.8088. Min Act: -0.0000

Data Index: 809126 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.7966. Min Act: -0.0000

Data Index: 620825 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.2368. Min Act: -0.0000

Data Index: 963569 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.3793. Min Act: -0.0000

Data Index: 976880 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.2110. Min Act: -0.0000

Data Index: 357131 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.1641. Min Act: -0.0000

Data Index: 827638 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.0885. Min Act: -0.0000

Data Index: 438615 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.8619. Min Act: -0.0000

Data Index: 166370 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 5.1398. Min Range: -5.1398

Max Act: 4.0253. Min Act: -0.0000

Data Index: 531502 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.9318. Min Act: -0.0000

Data Index: 857256 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.6925. Min Act: -0.0000

Data Index: 31700 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.6582. Min Act: -0.0000

Data Index: 600573 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.8951. Min Act: -0.0000

Data Index: 20107 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.7421. Min Act: -0.0000

Data Index: 45655 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.7072. Min Act: -0.0000

Data Index: 1266385 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 5.1398. Min Range: -5.1398

Max Act: 3.7169. Min Act: -0.0000

Data Index: 40119 (C4 (Web Text))

Max Activating Token Index: 232