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

Dataset: The Pile

Neuron 1570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.7925. Min Act: -0.0000

Data Index: 1542727 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.7108. Min Act: -0.0000

Data Index: 1110815 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1836308 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1413187 (The Pile)

Max Activating Token Index: 42

Text #4

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1077429 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.6316. Min Act: -0.0000

Data Index: 958685 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5819. Min Act: -0.0000

Data Index: 235760 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4550. Min Act: -0.0000

Data Index: 634172 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5005. Min Act: -0.0000

Data Index: 488914 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5416. Min Act: -0.0000

Data Index: 800937 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5456. Min Act: -0.0000

Data Index: 832875 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1235296 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1876916 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4480. Min Act: -0.0000

Data Index: 375649 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1639273 (The Pile)

Max Activating Token Index: 928

Text #15

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1750988 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.2997. Min Act: -0.0000

Data Index: 648354 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1823595 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4715. Min Act: -0.0000

Data Index: 394143 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 1.7925. Min Range: -1.7925

Max Act: 1.4679. Min Act: -0.0000

Data Index: 845975 (The Pile)

Max Activating Token Index: 507