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

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

Neuron 3910 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1219431 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1529. Min Act: -0.0000

Data Index: 350375 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1470. Min Act: -0.0000

Data Index: 419112 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1290. Min Act: -0.0000

Data Index: 40536 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1318. Min Act: -0.0000

Data Index: 761574 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1351. Min Act: -0.0000

Data Index: 186035 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1163. Min Act: -0.0000

Data Index: 778770 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1205. Min Act: -0.0000

Data Index: 397412 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1339093 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1198161 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1207. Min Act: -0.0000

Data Index: 455535 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1268074 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1177. Min Act: -0.0000

Data Index: 181358 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1114612 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1088. Min Act: -0.0000

Data Index: 62946 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1244665 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.0982. Min Act: -0.0000

Data Index: 438337 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1013. Min Act: -0.0000

Data Index: 511209 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1220001 (C4 (Web Text))

Max Activating Token Index: 706