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

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

Neuron 3401 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1352087 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.3621. Min Act: -0.0000

Data Index: 827726 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.3383. Min Act: -0.0000

Data Index: 347665 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.3091. Min Act: -0.0000

Data Index: 703146 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2755. Min Act: -0.0000

Data Index: 33517 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2905. Min Act: -0.0000

Data Index: 875619 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2749. Min Act: -0.0000

Data Index: 48501 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1193305 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1340316 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1217969 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2437. Min Act: -0.0000

Data Index: 266010 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2503. Min Act: 0.0001

Data Index: 1243675 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2530. Min Act: -0.0000

Data Index: 923125 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1125175 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2388. Min Act: -0.0000

Data Index: 463296 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2565. Min Act: -0.0000

Data Index: 548826 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2156. Min Act: -0.0000

Data Index: 343050 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2394. Min Act: -0.0000

Data Index: 75238 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2315. Min Act: -0.0000

Data Index: 775480 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.3812. Min Range: -0.3812

Max Act: 0.2389. Min Act: -0.0000

Data Index: 892891 (C4 (Web Text))

Max Activating Token Index: 839