Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2490 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0004

Data Index: 265966 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0004

Data Index: 252458 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0003

Data Index: 113059 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1350894 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0003

Data Index: 608076 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 427006 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1233686 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0003

Data Index: 446204 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 357959 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0004

Data Index: 46312 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0004

Data Index: 910773 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 755469 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0004

Data Index: 601963 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0003

Data Index: 452873 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0003

Data Index: 213201 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 299848 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 653423 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0004

Data Index: 521896 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 863285 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1277953 (C4 (Web Text))

Max Activating Token Index: 251