Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.2254. Min Act: -0.0000

Data Index: 929015 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1157412 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1426. Min Act: -0.0000

Data Index: 653194 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1376. Min Act: -0.0000

Data Index: 588185 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1092446 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1262. Min Act: -0.0000

Data Index: 271497 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1027793 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1250. Min Act: -0.0000

Data Index: 934303 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1541808 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1160. Min Act: -0.0000

Data Index: 546354 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1107449 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1135. Min Act: -0.0000

Data Index: 209099 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1042. Min Act: -0.0000

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1080. Min Act: -0.0000

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1102. Min Act: -0.0001

Data Index: 238255 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1057. Min Act: -0.0000

Data Index: 230975 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1492569 (Python Code)

Max Activating Token Index: 410

Text #17

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1026. Min Act: -0.0000

Data Index: 26394 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1103531 (C4 (Web Text))

Max Activating Token Index: 671