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

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

Neuron 1980 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: 0.1413. Min Range: -0.1413

Max Act: 0.1324. Min Act: -0.0002

Data Index: 413372 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1413. Min Act: -0.0001

Data Index: 101856 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1251. Min Act: -0.0002

Data Index: 137363 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1255. Min Act: -0.0002

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1003661 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1291. Min Act: -0.0001

Data Index: 595374 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1072548 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1191. Min Act: -0.0002

Data Index: 95253 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1106. Min Act: -0.0002

Data Index: 6586 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1188. Min Act: -0.0002

Data Index: 50167 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1216. Min Act: -0.0001

Data Index: 168337 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1083. Min Act: -0.0001

Data Index: 225692 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1164. Min Act: -0.0002

Data Index: 344461 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1185. Min Act: -0.0002

Data Index: 246014 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1226583 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1166. Min Act: -0.0002

Data Index: 647713 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1160. Min Act: -0.0001

Data Index: 776339 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1028551 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1111. Min Act: -0.0002

Data Index: 106803 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.1413. Min Range: -0.1413

Max Act: 0.1088. Min Act: -0.0001

Data Index: 185983 (C4 (Web Text))

Max Activating Token Index: 281