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

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

Neuron 675 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0580. Min Act: -0.0000

Data Index: 863530 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0695. Min Act: -0.0000

Data Index: 408977 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 1.0695. Min Range: -1.0695

Max Act: 1.0319. Min Act: -0.0000

Data Index: 762388 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1511536 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9238. Min Act: -0.0000

Data Index: 456012 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8212. Min Act: -0.0000

Data Index: 789094 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9439. Min Act: -0.0000

Data Index: 112669 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1138670 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8759. Min Act: -0.0000

Data Index: 145074 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8277. Min Act: -0.0000

Data Index: 876010 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8783. Min Act: -0.0000

Data Index: 363878 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8451. Min Act: -0.0000

Data Index: 579325 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1190257 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8477. Min Act: -0.0000

Data Index: 205553 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7282. Min Act: -0.0000

Data Index: 1224598 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7722. Min Act: -0.0000

Data Index: 541370 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8022. Min Act: -0.0000

Data Index: 578017 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1426125 (Python Code)

Max Activating Token Index: 567

Text #18

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1139620 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7877. Min Act: -0.0000

Data Index: 916720 (C4 (Web Text))

Max Activating Token Index: 67