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

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

Neuron 1915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.1453. Min Act: -0.0000

Data Index: 294094 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0829. Min Act: -0.0000

Data Index: 561942 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1165355 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0534. Min Act: -0.0000

Data Index: 993297 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0573. Min Act: -0.0000

Data Index: 229148 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0522. Min Act: -0.0000

Data Index: 451528 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.1453. Min Range: -1.1453

Max Act: 1.0061. Min Act: -0.0000

Data Index: 576209 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9937. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1305968 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9672. Min Act: -0.0000

Data Index: 439429 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9031. Min Act: -0.0000

Data Index: 916047 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9449. Min Act: -0.0000

Data Index: 621038 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1259203 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1039541 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9371. Min Act: -0.0000

Data Index: 373922 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9906. Min Act: -0.0000

Data Index: 8775 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.7622. Min Act: -0.0000

Data Index: 662136 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.9120. Min Act: -0.0000

Data Index: 770981 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.8756. Min Act: -0.0000

Data Index: 549349 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.1453. Min Range: -1.1453

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1114127 (C4 (Web Text))

Max Activating Token Index: 804