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

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

Neuron 5564 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.9283. Min Act: 0.0000

Data Index: 266189 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7701. Min Act: -0.0000

Data Index: 242824 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7797. Min Act: -0.0000

Data Index: 814379 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7745. Min Act: 0.0000

Data Index: 296928 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.7061. Min Act: 0.0000

Data Index: 608030 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6832. Min Act: -0.0000

Data Index: 520596 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6902. Min Act: -0.0000

Data Index: 17332 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6479. Min Act: -0.0000

Data Index: 791431 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6753. Min Act: -0.0000

Data Index: 588750 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6553. Min Act: -0.0000

Data Index: 753660 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6641. Min Act: -0.0000

Data Index: 395758 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1488280 (Python Code)

Max Activating Token Index: 500

Text #12

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6752. Min Act: -0.0000

Data Index: 546327 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6652. Min Act: -0.0000

Data Index: 981858 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6588. Min Act: -0.0000

Data Index: 216417 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6573. Min Act: 0.0000

Data Index: 1040297 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6007. Min Act: -0.0000

Data Index: 795507 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1556450 (Python Code)

Max Activating Token Index: 936

Text #18

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1477857 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 0.9283. Min Range: -0.9283

Max Act: 0.6445. Min Act: 0.0000

Data Index: 520980 (C4 (Web Text))

Max Activating Token Index: 199