Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2896 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.3210. Min Act: -0.0002

Data Index: 693621 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2477. Min Act: -0.0003

Data Index: 1103143 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2486. Min Act: -0.0003

Data Index: 737657 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2308. Min Act: -0.0003

Data Index: 683445 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2290. Min Act: -0.0003

Data Index: 388311 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2267. Min Act: -0.0003

Data Index: 727659 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2244. Min Act: -0.0002

Data Index: 166769 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2234. Min Act: -0.0003

Data Index: 255980 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2222. Min Act: -0.0003

Data Index: 591584 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2111. Min Act: -0.0003

Data Index: 41043 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2108. Min Act: -0.0003

Data Index: 615858 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2100. Min Act: -0.0003

Data Index: 642144 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2024. Min Act: -0.0002

Data Index: 1320864 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2097. Min Act: -0.0003

Data Index: 87945 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2089. Min Act: -0.0003

Data Index: 528925 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2084. Min Act: -0.0003

Data Index: 102863 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2070. Min Act: -0.0002

Data Index: 110991 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2064. Min Act: -0.0003

Data Index: 1231425 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2039. Min Act: -0.0003

Data Index: 983037 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2038. Min Act: -0.0003

Data Index: 1269445 (C4 (Web Text))

Max Activating Token Index: 218