Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5072 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 12.7095. Min Range: -12.7095

Max Act: 12.7095. Min Act: -0.0000

Data Index: 936257 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 12.7095. Min Range: -12.7095

Max Act: 12.2946. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.8472. Min Act: -0.0000

Data Index: 722505 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 12.7095. Min Range: -12.7095

Max Act: 12.0478. Min Act: -0.0000

Data Index: 182762 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.9700. Min Act: -0.0000

Data Index: 562604 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.5773. Min Act: -0.0000

Data Index: 783567 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.1211. Min Act: -0.0000

Data Index: 1161682 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.4958. Min Act: -0.0000

Data Index: 1039750 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.5551. Min Act: -0.0000

Data Index: 452007 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.5378. Min Act: -0.0000

Data Index: 287014 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.1507. Min Act: -0.0000

Data Index: 221572 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.2492. Min Act: -0.0000

Data Index: 808528 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.0646. Min Act: -0.0000

Data Index: 4160 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.2919. Min Act: -0.0000

Data Index: 1029598 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 12.7095. Min Range: -12.7095

Max Act: 10.9246. Min Act: -0.0000

Data Index: 725172 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 12.7095. Min Range: -12.7095

Max Act: 10.5307. Min Act: -0.0000

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.1105. Min Act: -0.0000

Data Index: 64664 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 12.7095. Min Range: -12.7095

Max Act: 11.2666. Min Act: -0.0000

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 12.7095. Min Range: -12.7095

Max Act: 10.7295. Min Act: -0.0000

Data Index: 1033866 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 12.7095. Min Range: -12.7095

Max Act: 10.3821. Min Act: -0.0000

Data Index: 669448 (C4 (Web Text))

Max Activating Token Index: 917