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

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

Neuron 5004 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.7325. Min Act: -0.0002

Data Index: 832165 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.6053. Min Act: -0.0002

Data Index: 1046964 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5930. Min Act: -0.0002

Data Index: 195541 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5827. Min Act: -0.0002

Data Index: 1182386 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5868. Min Act: -0.0002

Data Index: 747535 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5702. Min Act: -0.0002

Data Index: 327353 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5720. Min Act: -0.0002

Data Index: 713817 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5863. Min Act: -0.0002

Data Index: 599842 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5841. Min Act: -0.0002

Data Index: 765850 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5477. Min Act: -0.0002

Data Index: 593896 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5082. Min Act: -0.0002

Data Index: 1308371 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5285. Min Act: -0.0002

Data Index: 742986 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5624. Min Act: -0.0002

Data Index: 170753 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5123. Min Act: -0.0002

Data Index: 1073890 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5537. Min Act: -0.0002

Data Index: 1310801 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5814. Min Act: -0.0002

Data Index: 796367 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5549. Min Act: -0.0002

Data Index: 1208280 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4641. Min Act: -0.0002

Data Index: 817533 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5314. Min Act: -0.0002

Data Index: 889444 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4896. Min Act: -0.0002

Data Index: 843231 (C4 (Web Text))

Max Activating Token Index: 573