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

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

Neuron 1472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2525. Min Act: -0.0001

Data Index: 200790 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.3750. Min Act: -0.0001

Data Index: 50574 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.3408. Min Act: -0.0001

Data Index: 527104 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2469. Min Act: -0.0000

Data Index: 565879 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2359. Min Act: -0.0000

Data Index: 399117 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2672. Min Act: -0.0001

Data Index: 266345 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2223. Min Act: -0.0001

Data Index: 596478 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.1803. Min Act: -0.0000

Data Index: 845580 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2415. Min Act: -0.0000

Data Index: 636513 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.2183. Min Act: -0.0001

Data Index: 789448 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.0956. Min Act: -0.0001

Data Index: 620003 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.0017. Min Act: -0.0001

Data Index: 634254 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.1640. Min Act: -0.0001

Data Index: 606955 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.0925. Min Act: -0.0001

Data Index: 401029 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.1272. Min Act: -0.0001

Data Index: 682853 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.1014. Min Act: -0.0001

Data Index: 425643 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.1178. Min Act: -0.0000

Data Index: 3399 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.0789. Min Act: -0.0001

Data Index: 220976 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.3750. Min Range: -1.3750

Max Act: 0.9329. Min Act: -0.0001

Data Index: 268976 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.3750. Min Range: -1.3750

Max Act: 1.0707. Min Act: -0.0000

Data Index: 875984 (C4 (Web Text))

Max Activating Token Index: 48