Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3828 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2952. Min Act: -0.0000

Data Index: 228862 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.2561. Min Act: -0.0000

Data Index: 110386 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.9563. Min Act: -0.0000

Data Index: 448917 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.2952. Min Range: -1.2952

Max Act: 1.0056. Min Act: -0.0000

Data Index: 886160 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.9645. Min Act: -0.0000

Data Index: 716754 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.9991. Min Act: -0.0000

Data Index: 837200 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8977. Min Act: -0.0000

Data Index: 949968 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.9614. Min Act: -0.0000

Data Index: 68756 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1198677 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8966. Min Act: -0.0000

Data Index: 313752 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1193313 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8818. Min Act: -0.0000

Data Index: 518381 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8392. Min Act: -0.0000

Data Index: 852587 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.7583. Min Act: -0.0000

Data Index: 343132 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.7665. Min Act: -0.0000

Data Index: 979104 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8139. Min Act: -0.0000

Data Index: 361196 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8127. Min Act: -0.0000

Data Index: 530118 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8392. Min Act: -0.0000

Data Index: 707737 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8146. Min Act: -0.0000

Data Index: 332484 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 1.2952. Min Range: -1.2952

Max Act: 0.8344. Min Act: -0.0000

Data Index: 500759 (C4 (Web Text))

Max Activating Token Index: 291