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

Dataset: The Pile

Neuron 1269 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1273940 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9987. Min Act: -0.0000

Data Index: 942016 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0294. Min Act: -0.0000

Data Index: 559084 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0043. Min Act: -0.0000

Data Index: 291528 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0228. Min Act: -0.0000

Data Index: 666121 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0684. Min Act: -0.0000

Data Index: 362085 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0101. Min Act: -0.0000

Data Index: 792083 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9788. Min Act: -0.0000

Data Index: 792581 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9327. Min Act: -0.0000

Data Index: 568489 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0166. Min Act: -0.0000

Data Index: 935617 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1175849 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1382403 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9641. Min Act: -0.0000

Data Index: 708197 (The Pile)

Max Activating Token Index: 163

Text #13

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9320. Min Act: -0.0000

Data Index: 382654 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9607. Min Act: -0.0000

Data Index: 285590 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1474959 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8672. Min Act: -0.0000

Data Index: 362767 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1642791 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8667. Min Act: -0.0000

Data Index: 381023 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1120843 (The Pile)

Max Activating Token Index: 41