Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 348 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0005

Data Index: 106804 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0211. Min Act: -0.0005

Data Index: 52352 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1596483 (Python Code)

Max Activating Token Index: 710

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1397666 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0151. Min Act: -0.0005

Data Index: 735955 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0154. Min Act: -0.0005

Data Index: 1225901 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0150. Min Act: -0.0005

Data Index: 1554651 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1574076 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1623006 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1404990 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1012267 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1619879 (Python Code)

Max Activating Token Index: 275

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0118. Min Act: -0.0005

Data Index: 853820 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0116. Min Act: -0.0005

Data Index: 142342 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0117. Min Act: -0.0006

Data Index: 573422 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1158621 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0111. Min Act: -0.0005

Data Index: 226299 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1121879 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1303775 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1403503 (Python Code)

Max Activating Token Index: 912