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

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

Neuron 3536 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: 0.7373. Min Range: -0.7373

Max Act: 0.6822. Min Act: -0.0001

Data Index: 1297865 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.7373. Min Act: -0.0002

Data Index: 160745 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5887. Min Act: -0.0001

Data Index: 178667 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6342. Min Act: -0.0002

Data Index: 1044003 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1066491 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6237. Min Act: -0.0001

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6524. Min Act: -0.0002

Data Index: 1257600 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6089. Min Act: -0.0002

Data Index: 404134 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6062. Min Act: -0.0002

Data Index: 1143067 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5669. Min Act: -0.0002

Data Index: 657000 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5614. Min Act: -0.0001

Data Index: 235235 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5806. Min Act: -0.0002

Data Index: 880645 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6025. Min Act: -0.0002

Data Index: 470652 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5619. Min Act: -0.0001

Data Index: 639433 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5910. Min Act: -0.0001

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5943. Min Act: -0.0002

Data Index: 504658 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1310727 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5636. Min Act: -0.0001

Data Index: 621359 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.6095. Min Act: -0.0002

Data Index: 646872 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.7373. Min Range: -0.7373

Max Act: 0.5758. Min Act: -0.0001

Data Index: 1283707 (C4 (Web Text))

Max Activating Token Index: 287