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

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

Neuron 5127 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8595. Min Act: -0.0000

Data Index: 369364 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8122. Min Act: -0.0000

Data Index: 241632 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1116599 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7998. Min Act: -0.0000

Data Index: 105726 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7502. Min Act: -0.0000

Data Index: 311668 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7411. Min Act: -0.0000

Data Index: 804051 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7268. Min Act: -0.0000

Data Index: 15989 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6780. Min Act: -0.0000

Data Index: 311597 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8344. Min Act: -0.0000

Data Index: 20368 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.8079. Min Act: -0.0000

Data Index: 733144 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6906. Min Act: -0.0000

Data Index: 665450 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7015. Min Act: -0.0000

Data Index: 840042 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6411. Min Act: -0.0000

Data Index: 463733 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6813. Min Act: -0.0000

Data Index: 267604 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6786. Min Act: -0.0000

Data Index: 77625 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7169. Min Act: -0.0000

Data Index: 303629 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1088346 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6677. Min Act: -0.0000

Data Index: 547785 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1200898 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.8595. Min Range: -0.8595

Max Act: 0.7155. Min Act: -0.0000

Data Index: 320779 (C4 (Web Text))

Max Activating Token Index: 296