Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2563 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1136869 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0002

Data Index: 1060231 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2417. Min Act: -0.0001

Data Index: 641535 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1151308 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2315. Min Act: -0.0001

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2363. Min Act: -0.0001

Data Index: 745154 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2297. Min Act: -0.0001

Data Index: 99010 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2114. Min Act: -0.0002

Data Index: 484905 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2278. Min Act: -0.0001

Data Index: 956787 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2172. Min Act: -0.0001

Data Index: 597246 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1079426 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2088. Min Act: -0.0001

Data Index: 1349423 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2096. Min Act: -0.0002

Data Index: 753615 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2064. Min Act: -0.0001

Data Index: 466217 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2107. Min Act: -0.0001

Data Index: 1308016 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2028. Min Act: -0.0002

Data Index: 328224 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2020. Min Act: -0.0002

Data Index: 254825 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2011. Min Act: -0.0001

Data Index: 176536 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1259450 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2034. Min Act: -0.0001

Data Index: 987334 (C4 (Web Text))

Max Activating Token Index: 208