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

Dataset: The Pile

Neuron 2411 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1611. Min Act: -0.0000

Data Index: 44995 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 3.1611. Min Range: -3.1611

Max Act: 2.1446. Min Act: -0.0000

Data Index: 1320620 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.9701. Min Act: -0.0000

Data Index: 1776541 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 3.1611. Min Range: -3.1611

Max Act: 2.0072. Min Act: 0.0000

Data Index: 719209 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.9280. Min Act: -0.0000

Data Index: 287932 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.8943. Min Act: -0.0000

Data Index: 1640850 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.8063. Min Act: -0.0000

Data Index: 884045 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1605437 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.7929. Min Act: -0.0000

Data Index: 326644 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1079664 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6627. Min Act: -0.0000

Data Index: 229252 (The Pile)

Max Activating Token Index: 911

Text #11

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1173660 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1706729 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6223. Min Act: -0.0000

Data Index: 592512 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6088. Min Act: -0.0000

Data Index: 492201 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.6789. Min Act: -0.0000

Data Index: 762296 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.5071. Min Act: -0.0000

Data Index: 549888 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.5047. Min Act: -0.0000

Data Index: 182393 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.3722. Min Act: -0.0000

Data Index: 963712 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 3.1611. Min Range: -3.1611

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1752754 (The Pile)

Max Activating Token Index: 972