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

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

Neuron 3738 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2938. Min Act: -0.0002

Data Index: 416809 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2959. Min Act: -0.0002

Data Index: 735883 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2724. Min Act: -0.0002

Data Index: 705638 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2972. Min Act: -0.0002

Data Index: 1315371 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2546. Min Act: -0.0002

Data Index: 1331434 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2664. Min Act: -0.0002

Data Index: 835485 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2279. Min Act: -0.0002

Data Index: 284503 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2893. Min Act: -0.0002

Data Index: 800641 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2545. Min Act: -0.0002

Data Index: 421897 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2927. Min Act: -0.0002

Data Index: 529178 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2756. Min Act: -0.0002

Data Index: 887991 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.3002. Min Act: -0.0002

Data Index: 1041572 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2499. Min Act: -0.0002

Data Index: 727273 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2957. Min Act: -0.0002

Data Index: 360623 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2680. Min Act: -0.0002

Data Index: 989896 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2753. Min Act: -0.0002

Data Index: 838611 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2526. Min Act: -0.0002

Data Index: 984706 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.3037. Min Act: -0.0002

Data Index: 403558 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2729. Min Act: -0.0002

Data Index: 1285573 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2390. Min Act: -0.0002

Data Index: 1319407 (C4 (Web Text))

Max Activating Token Index: 233