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

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

Neuron 821 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.8214. Min Act: -0.0000

Data Index: 110229 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.7221. Min Act: -0.0000

Data Index: 688231 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.5193. Min Act: -0.0000

Data Index: 762760 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.5215. Min Act: -0.0000

Data Index: 127821 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.4734. Min Act: -0.0000

Data Index: 958154 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.4072. Min Act: -0.0000

Data Index: 544430 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3863. Min Act: -0.0000

Data Index: 829976 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3833. Min Act: -0.0000

Data Index: 674587 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.4460. Min Act: -0.0000

Data Index: 902902 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3214. Min Act: -0.0000

Data Index: 988583 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3504. Min Act: -0.0000

Data Index: 166018 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3438. Min Act: -0.0000

Data Index: 929343 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1266368 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.2945. Min Act: -0.0000

Data Index: 325854 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3342. Min Act: -0.0000

Data Index: 758062 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3196. Min Act: -0.0000

Data Index: 495204 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.2397. Min Act: -0.0000

Data Index: 104203 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.2215. Min Act: -0.0000

Data Index: 447629 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1190771 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.8214. Min Range: -1.8214

Max Act: 1.3051. Min Act: -0.0000

Data Index: 637425 (C4 (Web Text))

Max Activating Token Index: 642