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

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

Neuron 3180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4004. Min Act: -0.0001

Data Index: 772862 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1001646 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1045173 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2933. Min Act: -0.0000

Data Index: 621649 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2966. Min Act: -0.0000

Data Index: 388313 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2919. Min Act: -0.0000

Data Index: 795117 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2954. Min Act: -0.0000

Data Index: 76475 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2797. Min Act: -0.0000

Data Index: 322886 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2713. Min Act: -0.0000

Data Index: 106377 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2875. Min Act: -0.0000

Data Index: 872033 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2684. Min Act: -0.0000

Data Index: 65507 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2676. Min Act: -0.0001

Data Index: 749159 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2560. Min Act: -0.0000

Data Index: 867305 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2652. Min Act: -0.0000

Data Index: 423791 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2633. Min Act: -0.0000

Data Index: 990629 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2605. Min Act: -0.0000

Data Index: 817663 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1090085 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2677. Min Act: -0.0000

Data Index: 865216 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2458. Min Act: -0.0000

Data Index: 169607 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2453. Min Act: -0.0000

Data Index: 894484 (C4 (Web Text))

Max Activating Token Index: 1022