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

Dataset: The Pile

Neuron 335 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: 1.7055. Min Range: -1.7055

Max Act: 1.7055. Min Act: -0.0000

Data Index: 308134 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.6196. Min Act: -0.0000

Data Index: 733473 (The Pile)

Max Activating Token Index: 821

Text #2

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1034340 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.4511. Min Act: -0.0000

Data Index: 1427968 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.5266. Min Act: -0.0000

Data Index: 1431869 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.5271. Min Act: -0.0000

Data Index: 610998 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1644309 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1269488 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.3864. Min Act: -0.0000

Data Index: 71329 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1145693 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.4692. Min Act: -0.0000

Data Index: 1042655 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1927835 (The Pile)

Max Activating Token Index: 482

Text #12

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.3637. Min Act: -0.0000

Data Index: 334898 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.1767. Min Act: -0.0000

Data Index: 1425086 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1300592 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.3126. Min Act: -0.0000

Data Index: 619260 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1067018 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1733904 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.2886. Min Act: -0.0000

Data Index: 370468 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.7055. Min Range: -1.7055

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1808483 (The Pile)

Max Activating Token Index: 8