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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0003

Data Index: 551614 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0132. Min Act: -0.0003

Data Index: 211409 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1209 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1311664 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1326444 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0102. Min Act: -0.0004

Data Index: 344389 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0108. Min Act: -0.0003

Data Index: 726665 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0101. Min Act: -0.0003

Data Index: 780510 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0102. Min Act: -0.0003

Data Index: 16421 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0097. Min Act: -0.0003

Data Index: 706469 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1205768 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0103. Min Act: -0.0003

Data Index: 539879 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1005999 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1099291 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0104. Min Act: -0.0003

Data Index: 539463 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0101. Min Act: -0.0003

Data Index: 336616 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1299795 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0094. Min Act: -0.0004

Data Index: 718472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0085. Min Act: -0.0003

Data Index: 921202 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0102. Min Act: -0.0003

Data Index: 493526 (C4 (Web Text))

Max Activating Token Index: 801