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

Dataset: The Pile

Neuron 3083 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: 0.7938. Min Range: -0.7938

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1655614 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1570451 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7938. Min Act: -0.0000

Data Index: 661499 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1767337 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7579. Min Act: -0.0000

Data Index: 108840 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1033860 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7236. Min Act: -0.0000

Data Index: 217648 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1657082 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1924206 (The Pile)

Max Activating Token Index: 161

Text #9

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1272520 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1039861 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7052. Min Act: -0.0000

Data Index: 81558 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1666050 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6808. Min Act: -0.0001

Data Index: 320025 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1955650 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1747634 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.7027. Min Act: -0.0000

Data Index: 686770 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.5930. Min Act: 0.0000

Data Index: 138472 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6371. Min Act: -0.0000

Data Index: 146600 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.7938. Min Range: -0.7938

Max Act: 0.6756. Min Act: -0.0000

Data Index: 382844 (The Pile)

Max Activating Token Index: 883