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

Dataset: The Pile

Neuron 479 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: 0.6215. Min Range: -0.6215

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1860886 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1736342 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5790. Min Act: -0.0000

Data Index: 169273 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5733. Min Act: -0.0000

Data Index: 427232 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5338. Min Act: -0.0000

Data Index: 700346 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1738397 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5641. Min Act: -0.0000

Data Index: 442867 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1421448 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1692757 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5544. Min Act: -0.0000

Data Index: 893922 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5665. Min Act: -0.0000

Data Index: 699623 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5311. Min Act: -0.0000

Data Index: 137065 (The Pile)

Max Activating Token Index: 157

Text #12

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5230. Min Act: -0.0000

Data Index: 119991 (The Pile)

Max Activating Token Index: 302

Text #13

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4993. Min Act: -0.0000

Data Index: 804255 (The Pile)

Max Activating Token Index: 111

Text #14

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5129. Min Act: -0.0000

Data Index: 883096 (The Pile)

Max Activating Token Index: 282

Text #15

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1919183 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1585364 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1698530 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.5304. Min Act: -0.0000

Data Index: 518941 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.6215. Min Range: -0.6215

Max Act: 0.4700. Min Act: -0.0000

Data Index: 442256 (The Pile)

Max Activating Token Index: 499