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

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

Neuron 5054 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.2590. Min Act: -0.0000

Data Index: 157715 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.1729. Min Act: -0.0000

Data Index: 50809 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.1486. Min Act: -0.0000

Data Index: 705738 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1156251 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.0799. Min Act: -0.0000

Data Index: 480884 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.0992. Min Act: -0.0000

Data Index: 353629 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.0235. Min Act: -0.0000

Data Index: 8115 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9844. Min Act: -0.0000

Data Index: 441986 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1343447 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9654. Min Act: -0.0000

Data Index: 465345 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.2590. Min Range: -1.2590

Max Act: 1.0071. Min Act: -0.0000

Data Index: 631437 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9369. Min Act: -0.0000

Data Index: 338964 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1141853 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9490. Min Act: -0.0000

Data Index: 913537 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1242650 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.8814. Min Act: -0.0000

Data Index: 369328 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9032. Min Act: -0.0000

Data Index: 968911 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1020138 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.8747. Min Act: -0.0000

Data Index: 222002 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 1.2590. Min Range: -1.2590

Max Act: 0.8912. Min Act: -0.0000

Data Index: 460883 (C4 (Web Text))

Max Activating Token Index: 230