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

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

Neuron 2274 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.4170. Min Act: -0.0000

Data Index: 144760 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1247268 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2202. Min Act: -0.0000

Data Index: 734216 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2274. Min Act: -0.0000

Data Index: 987060 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2169. Min Act: -0.0000

Data Index: 527767 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1047921 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1278797 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2192. Min Act: -0.0000

Data Index: 64944 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2124. Min Act: -0.0000

Data Index: 564953 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1337683 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2126. Min Act: -0.0000

Data Index: 173342 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2054. Min Act: -0.0000

Data Index: 797079 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2037. Min Act: -0.0000

Data Index: 139555 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.2092. Min Act: -0.0000

Data Index: 734051 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1962. Min Act: -0.0000

Data Index: 754835 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1224892 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1206456 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1808. Min Act: -0.0000

Data Index: 727685 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1845. Min Act: -0.0000

Data Index: 807681 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.4170. Min Range: -0.4170

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1022995 (C4 (Web Text))

Max Activating Token Index: 313