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

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

Neuron 2419 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.1990. Min Act: -0.0000

Data Index: 628903 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.4224. Min Act: -0.0000

Data Index: 267037 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1133740 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.0307. Min Act: -0.0000

Data Index: 327855 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.2244. Min Act: -0.0000

Data Index: 641976 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.1883. Min Act: -0.0000

Data Index: 731683 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.1758. Min Act: -0.0000

Data Index: 746745 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.0215. Min Act: -0.0000

Data Index: 474630 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.0124. Min Act: -0.0000

Data Index: 730023 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.4224. Min Range: -2.4224

Max Act: 2.0476. Min Act: -0.0000

Data Index: 705521 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.8756. Min Act: -0.0000

Data Index: 75823 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.9033. Min Act: -0.0000

Data Index: 449983 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.7161. Min Act: -0.0000

Data Index: 327388 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.7824. Min Act: -0.0000

Data Index: 254005 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1242584 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.7576. Min Act: -0.0000

Data Index: 370259 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.4874. Min Act: -0.0000

Data Index: 291466 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.7539. Min Act: -0.0000

Data Index: 576906 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.5767. Min Act: -0.0000

Data Index: 982877 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 2.4224. Min Range: -2.4224

Max Act: 1.3768. Min Act: -0.0000

Data Index: 915894 (C4 (Web Text))

Max Activating Token Index: 865