Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3506 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1495888 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5825. Min Act: -0.0000

Data Index: 323448 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1373512 (Python Code)

Max Activating Token Index: 950

Text #3

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.6007. Min Act: -0.0000

Data Index: 880335 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3588. Min Act: -0.0000

Data Index: 86000 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2556. Min Act: -0.0000

Data Index: 979111 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3386. Min Act: -0.0000

Data Index: 454234 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1515414 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3126. Min Act: -0.0000

Data Index: 930589 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3657. Min Act: -0.0000

Data Index: 172277 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2447. Min Act: -0.0000

Data Index: 756993 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3210. Min Act: -0.0000

Data Index: 735205 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1532311 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1619318 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3112. Min Act: -0.0000

Data Index: 516218 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.3751. Min Act: -0.0000

Data Index: 1381396 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1109645 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2908. Min Act: -0.0000

Data Index: 1476046 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2872. Min Act: -0.0000

Data Index: 396723 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.8419. Min Range: -1.8419

Max Act: 1.2180. Min Act: -0.0000

Data Index: 372073 (C4 (Web Text))

Max Activating Token Index: 483