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

Dataset: The Pile

Neuron 1308 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1978638 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4931. Min Act: -0.0000

Data Index: 668533 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1396181 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1992245 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1314526 (The Pile)

Max Activating Token Index: 386

Text #5

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4692. Min Act: -0.0000

Data Index: 182023 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4554. Min Act: -0.0000

Data Index: 758362 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1690059 (The Pile)

Max Activating Token Index: 919

Text #8

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4500. Min Act: -0.0000

Data Index: 72060 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1063865 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4400. Min Act: -0.0000

Data Index: 85968 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4531. Min Act: -0.0000

Data Index: 996304 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4353. Min Act: -0.0000

Data Index: 438261 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4478. Min Act: -0.0000

Data Index: 833257 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1561139 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1543162 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1266189 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1668954 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1510631 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1006376 (The Pile)

Max Activating Token Index: 733