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

Dataset: The Pile

Neuron 2977 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: 1.0499. Min Range: -1.0499

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1792733 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.9759. Min Act: -0.0000

Data Index: 115881 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1545541 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1481256 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8431. Min Act: -0.0000

Data Index: 550335 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8513. Min Act: -0.0000

Data Index: 976901 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1510196 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1546822 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7782. Min Act: -0.0000

Data Index: 429008 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1637439 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7771. Min Act: -0.0000

Data Index: 1870527 (The Pile)

Max Activating Token Index: 743

Text #11

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7975. Min Act: -0.0000

Data Index: 248700 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7664. Min Act: -0.0000

Data Index: 226600 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7571. Min Act: -0.0000

Data Index: 975967 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1497444 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1190605 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7258. Min Act: -0.0000

Data Index: 6556 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6994. Min Act: -0.0000

Data Index: 48656 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7886. Min Act: -0.0000

Data Index: 152478 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6967. Min Act: -0.0000

Data Index: 733805 (The Pile)

Max Activating Token Index: 779