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

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

Neuron 388 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: 1.0271. Min Range: -1.0271

Max Act: 1.0271. Min Act: -0.0000

Data Index: 641418 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.9920. Min Act: -0.0000

Data Index: 365802 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.9928. Min Act: -0.0000

Data Index: 76136 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.9017. Min Act: -0.0000

Data Index: 29227 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8554. Min Act: -0.0000

Data Index: 505122 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8559. Min Act: -0.0000

Data Index: 468476 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8363. Min Act: -0.0000

Data Index: 257225 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1269947 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7977. Min Act: -0.0000

Data Index: 261704 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7154. Min Act: -0.0000

Data Index: 870354 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8042. Min Act: -0.0000

Data Index: 528584 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7438. Min Act: -0.0000

Data Index: 8052 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7611. Min Act: -0.0000

Data Index: 818052 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1095567 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7581. Min Act: -0.0000

Data Index: 342358 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7528. Min Act: -0.0000

Data Index: 483502 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8192. Min Act: -0.0000

Data Index: 238371 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7603. Min Act: -0.0000

Data Index: 789858 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7542. Min Act: -0.0000

Data Index: 62186 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7097. Min Act: -0.0000

Data Index: 314214 (C4 (Web Text))

Max Activating Token Index: 307