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

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

Neuron 398 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: 0.2766. Min Range: -0.2766

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1290531 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2567. Min Act: -0.0000

Data Index: 573012 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1041226 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2577. Min Act: -0.0001

Data Index: 573408 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2389. Min Act: -0.0000

Data Index: 160703 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2562. Min Act: -0.0000

Data Index: 22178 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2377. Min Act: -0.0000

Data Index: 922094 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2433. Min Act: -0.0001

Data Index: 741018 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1425132 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2481. Min Act: -0.0001

Data Index: 969096 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2496. Min Act: -0.0000

Data Index: 962294 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1331147 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2388. Min Act: -0.0001

Data Index: 840750 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1600526 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2416. Min Act: -0.0000

Data Index: 391732 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2423. Min Act: -0.0000

Data Index: 122080 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2412. Min Act: -0.0000

Data Index: 604002 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1010570 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2491. Min Act: -0.0001

Data Index: 474365 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1141343 (C4 (Web Text))

Max Activating Token Index: 56