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

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

Neuron 5905 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: 0.1360. Min Range: -0.1360

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1276098 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1332. Min Act: -0.0000

Data Index: 522694 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1360. Min Act: -0.0000

Data Index: 817666 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1172. Min Act: -0.0000

Data Index: 225468 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1286152 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1266. Min Act: -0.0000

Data Index: 6144 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1231. Min Act: -0.0000

Data Index: 546068 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1127. Min Act: -0.0000

Data Index: 95431 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1184. Min Act: -0.0000

Data Index: 160069 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1277252 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1220. Min Act: -0.0000

Data Index: 446160 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1101. Min Act: -0.0000

Data Index: 98170 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1088. Min Act: -0.0000

Data Index: 271270 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1449280 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1040317 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1039486 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1131572 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.0990. Min Act: -0.0000

Data Index: 626181 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1581282 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.1360. Min Range: -0.1360

Max Act: 0.1064. Min Act: -0.0000

Data Index: 178905 (C4 (Web Text))

Max Activating Token Index: 712