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

Dataset: The Pile

Neuron 2243 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: 0.7391. Min Range: -0.7391

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1183880 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1149398 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6870. Min Act: -0.0000

Data Index: 996653 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5823. Min Act: -0.0000

Data Index: 399429 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5680. Min Act: -0.0000

Data Index: 279121 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6027. Min Act: -0.0000

Data Index: 28315 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1957309 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5335. Min Act: -0.0000

Data Index: 570412 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6042. Min Act: -0.0000

Data Index: 522741 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1990508 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6127. Min Act: -0.0000

Data Index: 341183 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5673. Min Act: -0.0000

Data Index: 288156 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5874. Min Act: -0.0000

Data Index: 811133 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6030. Min Act: -0.0000

Data Index: 623974 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1969303 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1443395 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1913379 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1841211 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5415. Min Act: -0.0000

Data Index: 305581 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5237. Min Act: -0.0000

Data Index: 243296 (The Pile)

Max Activating Token Index: 424