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

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

Neuron 3371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1697. Min Act: -0.0002

Data Index: 766026 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8778. Min Act: -0.0001

Data Index: 1175541 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1029. Min Act: -0.0001

Data Index: 165464 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8944. Min Act: -0.0001

Data Index: 505795 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8996. Min Act: -0.0001

Data Index: 221450 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8257. Min Act: -0.0001

Data Index: 620713 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9395. Min Act: -0.0001

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9373. Min Act: -0.0001

Data Index: 184544 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8189. Min Act: -0.0002

Data Index: 274814 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8737. Min Act: -0.0002

Data Index: 155604 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8867. Min Act: -0.0001

Data Index: 291715 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8341. Min Act: -0.0001

Data Index: 1042999 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8302. Min Act: -0.0002

Data Index: 1305919 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1106260 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8278. Min Act: -0.0002

Data Index: 662901 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8202. Min Act: -0.0001

Data Index: 236315 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8115. Min Act: -0.0001

Data Index: 869652 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8664. Min Act: -0.0001

Data Index: 217248 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8430. Min Act: -0.0001

Data Index: 372906 (C4 (Web Text))

Max Activating Token Index: 935