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

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

Neuron 5092 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: 0.7842. Min Range: -0.7842

Max Act: 0.7842. Min Act: 0.0000

Data Index: 969698 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7502. Min Act: -0.0000

Data Index: 46691 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7122. Min Act: -0.0000

Data Index: 554523 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6836. Min Act: -0.0000

Data Index: 723051 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6956. Min Act: -0.0000

Data Index: 251349 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6758. Min Act: -0.0000

Data Index: 564331 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1291245 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6688. Min Act: -0.0000

Data Index: 168370 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1196482 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6033. Min Act: -0.0000

Data Index: 480438 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1076061 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6644. Min Act: -0.0000

Data Index: 104171 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6603. Min Act: -0.0000

Data Index: 810655 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6568. Min Act: -0.0000

Data Index: 402910 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6421. Min Act: -0.0000

Data Index: 959225 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6762. Min Act: -0.0000

Data Index: 256561 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6599. Min Act: -0.0000

Data Index: 411850 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6695. Min Act: -0.0000

Data Index: 169190 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6485. Min Act: -0.0000

Data Index: 527090 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6673. Min Act: -0.0000

Data Index: 97531 (C4 (Web Text))

Max Activating Token Index: 601