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

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

Neuron 3574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.4573. Min Act: -0.0000

Data Index: 1081648 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.5477. Min Act: -0.0000

Data Index: 368723 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.3933. Min Act: -0.0000

Data Index: 374756 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.2699. Min Act: -0.0000

Data Index: 455190 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.3449. Min Act: -0.0000

Data Index: 88138 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.3048. Min Act: -0.0000

Data Index: 901526 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.1802. Min Act: -0.0000

Data Index: 685531 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.1914. Min Act: -0.0000

Data Index: 498763 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.0553. Min Act: -0.0000

Data Index: 894626 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.0408. Min Act: -0.0000

Data Index: 1068441 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.0317. Min Act: -0.0000

Data Index: 427115 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.9780. Min Act: -0.0000

Data Index: 764168 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 2.5477. Min Range: -2.5477

Max Act: 2.0390. Min Act: -0.0000

Data Index: 584945 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.8514. Min Act: -0.0000

Data Index: 867895 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.7830. Min Act: -0.0000

Data Index: 990713 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.6974. Min Act: -0.0000

Data Index: 650900 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.6726. Min Act: -0.0000

Data Index: 894304 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.6829. Min Act: -0.0000

Data Index: 787643 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.6923. Min Act: -0.0000

Data Index: 316708 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 2.5477. Min Range: -2.5477

Max Act: 1.6778. Min Act: -0.0000

Data Index: 956475 (C4 (Web Text))

Max Activating Token Index: 953