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

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

Neuron 4267 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.8144. Min Act: -0.0001

Data Index: 1230766 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.4714. Min Act: -0.0000

Data Index: 1245701 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.3121. Min Act: -0.0000

Data Index: 777149 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.4140. Min Act: -0.0000

Data Index: 904222 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.3132. Min Act: -0.0000

Data Index: 510093 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1364. Min Act: -0.0000

Data Index: 695721 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1484. Min Act: -0.0000

Data Index: 556754 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.0862. Min Act: -0.0000

Data Index: 1138862 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1898. Min Act: -0.0000

Data Index: 300798 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.8144. Min Range: -2.8144

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1349667 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1140. Min Act: -0.0000

Data Index: 65310 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.0928. Min Act: -0.0000

Data Index: 511974 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.0886. Min Act: -0.0000

Data Index: 1235421 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.3147. Min Act: -0.0000

Data Index: 1265661 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.0829. Min Act: -0.0000

Data Index: 424026 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1921. Min Act: -0.0000

Data Index: 1027884 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.0502. Min Act: -0.0000

Data Index: 66251 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.8144. Min Range: -2.8144

Max Act: 1.8195. Min Act: -0.0000

Data Index: 1197869 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1334. Min Act: -0.0000

Data Index: 300020 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 2.8144. Min Range: -2.8144

Max Act: 2.1363. Min Act: -0.0000

Data Index: 138111 (C4 (Web Text))

Max Activating Token Index: 949