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

Dataset: The Pile

Neuron 213 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1720. Min Range: -5.1720

Max Act: 5.1720. Min Act: -0.0000

Data Index: 1001496 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 5.1720. Min Range: -5.1720

Max Act: 5.0859. Min Act: -0.0000

Data Index: 1562249 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 5.1720. Min Range: -5.1720

Max Act: 5.0085. Min Act: -0.0000

Data Index: 54276 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.9162. Min Act: -0.0000

Data Index: 751076 (The Pile)

Max Activating Token Index: 160

Text #4

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.4901. Min Act: -0.0000

Data Index: 523228 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.2356. Min Act: -0.0000

Data Index: 1046823 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.3526. Min Act: -0.0000

Data Index: 929253 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5061. Min Act: -0.0000

Data Index: 1547289 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 5.1720. Min Range: -5.1720

Max Act: 3.8117. Min Act: -0.0000

Data Index: 1676042 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.4713. Min Act: -0.0000

Data Index: 913939 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.4420. Min Act: -0.0000

Data Index: 1473041 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.1036. Min Act: -0.0000

Data Index: 270673 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.2408. Min Act: -0.0000

Data Index: 1468537 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.2431. Min Act: -0.0000

Data Index: 1407534 (The Pile)

Max Activating Token Index: 450

Text #14

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.2352. Min Act: -0.0000

Data Index: 1442504 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.2002. Min Act: -0.0000

Data Index: 1759669 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.5387. Min Act: -0.0000

Data Index: 1185169 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.1728. Min Act: -0.0000

Data Index: 1353784 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 5.1720. Min Range: -5.1720

Max Act: 4.1661. Min Act: -0.0000

Data Index: 1150357 (The Pile)

Max Activating Token Index: 943

Text #19

Max Range: 5.1720. Min Range: -5.1720

Max Act: 3.9928. Min Act: -0.0000

Data Index: 513364 (The Pile)

Max Activating Token Index: 529