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

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

Neuron 3221 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: 3.6600. Min Range: -3.6600

Max Act: 3.5912. Min Act: -0.0000

Data Index: 525605 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.6600. Min Act: -0.0000

Data Index: 693007 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.6472. Min Act: -0.0000

Data Index: 225943 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.6168. Min Act: -0.0000

Data Index: 1095511 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.2584. Min Act: -0.0000

Data Index: 105066 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.0769. Min Act: -0.0000

Data Index: 870359 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.1952. Min Act: -0.0000

Data Index: 174674 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.3089. Min Act: -0.0000

Data Index: 717056 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.1598. Min Act: -0.0000

Data Index: 519771 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.2433. Min Act: -0.0000

Data Index: 771927 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 3.6600. Min Range: -3.6600

Max Act: 2.9025. Min Act: -0.0000

Data Index: 1040832 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.3285. Min Act: -0.0000

Data Index: 1009450 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.3342. Min Act: -0.0000

Data Index: 893775 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.0179. Min Act: -0.0000

Data Index: 601707 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 3.6600. Min Range: -3.6600

Max Act: 2.9733. Min Act: -0.0000

Data Index: 749729 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.1415. Min Act: -0.0000

Data Index: 917441 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.0893. Min Act: -0.0000

Data Index: 1029373 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.6600. Min Range: -3.6600

Max Act: 2.9363. Min Act: -0.0000

Data Index: 1180164 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 3.6600. Min Range: -3.6600

Max Act: 3.0172. Min Act: -0.0000

Data Index: 5421 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 3.6600. Min Range: -3.6600

Max Act: 2.8290. Min Act: -0.0000

Data Index: 1350264 (C4 (Web Text))

Max Activating Token Index: 881