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

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

Neuron 1067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3721. Min Act: -0.0000

Data Index: 646712 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1066354 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1277098 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3702. Min Act: -0.0001

Data Index: 212489 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3442. Min Act: -0.0000

Data Index: 333029 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3142. Min Act: -0.0000

Data Index: 394200 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3398. Min Act: -0.0000

Data Index: 565703 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3252. Min Act: -0.0000

Data Index: 935769 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1101183 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1280026 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2971. Min Act: -0.0001

Data Index: 1258764 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1265715 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1088036 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1353280 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2880. Min Act: -0.0000

Data Index: 512373 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2749. Min Act: -0.0000

Data Index: 413863 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2905. Min Act: -0.0000

Data Index: 202798 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2790. Min Act: -0.0000

Data Index: 2613 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1323561 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2456. Min Act: -0.0000

Data Index: 953668 (C4 (Web Text))

Max Activating Token Index: 149