Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3911. Min Act: -0.0000

Data Index: 694325 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1538648 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3089. Min Act: -0.0000

Data Index: 838197 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1905488 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1506641 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1485467 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2898. Min Act: -0.0000

Data Index: 670592 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2733. Min Act: -0.0000

Data Index: 158163 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2939. Min Act: -0.0000

Data Index: 539088 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2847. Min Act: -0.0000

Data Index: 739381 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1179236 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2857. Min Act: -0.0000

Data Index: 1150872 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1798026 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2621. Min Act: -0.0000

Data Index: 458088 (The Pile)

Max Activating Token Index: 12

Text #14

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2496. Min Act: -0.0000

Data Index: 366817 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2352. Min Act: -0.0000

Data Index: 920505 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2416. Min Act: -0.0000

Data Index: 811047 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2528. Min Act: 0.0000

Data Index: 1076878 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2469. Min Act: -0.0000

Data Index: 838419 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2446. Min Act: -0.0000

Data Index: 392035 (The Pile)

Max Activating Token Index: 850