Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1487 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.4707. Min Act: -0.0000

Data Index: 831632 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.4707. Min Act: -0.0000

Data Index: 175808 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.4580. Min Act: -0.0000

Data Index: 508384 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.4503. Min Act: -0.0000

Data Index: 456797 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1031340 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.3367. Min Act: -0.0000

Data Index: 794965 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.2300. Min Act: -0.0000

Data Index: 3847 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.2196. Min Act: -0.0000

Data Index: 503727 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.2173. Min Act: -0.0000

Data Index: 929754 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1763. Min Act: -0.0000

Data Index: 277567 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.2458. Min Act: -0.0000

Data Index: 735791 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1446025 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1076. Min Act: -0.0000

Data Index: 635947 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1046. Min Act: -0.0000

Data Index: 444352 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.0534. Min Act: -0.0000

Data Index: 409784 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1090. Min Act: -0.0000

Data Index: 435848 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1384138 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1140350 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.1398. Min Act: -0.0000

Data Index: 798439 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.4707. Min Range: -1.4707

Max Act: 1.0651. Min Act: -0.0000

Data Index: 366093 (C4 (Web Text))

Max Activating Token Index: 489