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

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

Neuron 5594 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: 2.7453. Min Range: -2.7453

Max Act: 2.7453. Min Act: -0.0001

Data Index: 1223325 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5332. Min Act: -0.0001

Data Index: 653767 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.6216. Min Act: -0.0001

Data Index: 1261776 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.4841. Min Act: -0.0000

Data Index: 1230122 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.3249. Min Act: -0.0001

Data Index: 81676 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.3866. Min Act: -0.0001

Data Index: 1319936 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.3165. Min Act: -0.0000

Data Index: 94720 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.2768. Min Act: -0.0000

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.2831. Min Act: -0.0001

Data Index: 1137447 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.1508. Min Act: -0.0001

Data Index: 1016048 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.0478. Min Act: -0.0000

Data Index: 867015 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.1715. Min Act: -0.0001

Data Index: 99550 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.5068. Min Act: -0.0001

Data Index: 1170606 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.2085. Min Act: -0.0000

Data Index: 339029 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.2196. Min Act: -0.0000

Data Index: 432516 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.0695. Min Act: -0.0000

Data Index: 1060579 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.1972. Min Act: -0.0000

Data Index: 1055163 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.0386. Min Act: -0.0001

Data Index: 1348677 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.1430. Min Act: -0.0000

Data Index: 1082910 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.7453. Min Range: -2.7453

Max Act: 2.1279. Min Act: -0.0001

Data Index: 501001 (C4 (Web Text))

Max Activating Token Index: 591