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

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

Neuron 3581 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1066849 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8778. Min Act: -0.0000

Data Index: 364511 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8413. Min Act: -0.0000

Data Index: 920343 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.8082. Min Act: -0.0000

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1121145 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6509. Min Act: -0.0000

Data Index: 878739 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1078845 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6813. Min Act: -0.0000

Data Index: 977777 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6198. Min Act: -0.0000

Data Index: 1045673 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.6127. Min Act: -0.0000

Data Index: 195206 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5979. Min Act: -0.0000

Data Index: 338042 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5858. Min Act: -0.0000

Data Index: 462067 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5293. Min Act: -0.0000

Data Index: 108392 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1111653 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5372. Min Act: -0.0000

Data Index: 457146 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5235. Min Act: -0.0000

Data Index: 524723 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.5480. Min Act: -0.0000

Data Index: 799786 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1277332 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.4798. Min Act: -0.0000

Data Index: 838426 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.8982. Min Range: -1.8982

Max Act: 1.3998. Min Act: -0.0000

Data Index: 474122 (C4 (Web Text))

Max Activating Token Index: 683