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

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

Neuron 3891 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.6630. Min Act: -0.0001

Data Index: 1047807 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.5503. Min Act: -0.0001

Data Index: 373385 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.3335. Min Act: -0.0001

Data Index: 1325934 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.3793. Min Act: -0.0001

Data Index: 112904 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.2762. Min Act: -0.0001

Data Index: 1245679 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.3688. Min Act: -0.0001

Data Index: 221661 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.3341. Min Act: -0.0001

Data Index: 1079898 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.2103. Min Act: -0.0001

Data Index: 144280 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.2065. Min Act: -0.0001

Data Index: 512126 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1043727 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.1685. Min Act: -0.0001

Data Index: 704825 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.1719. Min Act: -0.0001

Data Index: 1350096 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.0667. Min Act: -0.0001

Data Index: 272572 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.0628. Min Act: -0.0001

Data Index: 657312 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.1246. Min Act: -0.0001

Data Index: 1126032 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.6630. Min Range: -1.6630

Max Act: 0.9813. Min Act: -0.0001

Data Index: 761584 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.0129. Min Act: -0.0001

Data Index: 474147 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 1.6630. Min Range: -1.6630

Max Act: 1.0305. Min Act: -0.0001

Data Index: 1280908 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.6630. Min Range: -1.6630

Max Act: 0.9949. Min Act: -0.0001

Data Index: 682994 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.6630. Min Range: -1.6630

Max Act: 0.9997. Min Act: -0.0001

Data Index: 1057544 (C4 (Web Text))

Max Activating Token Index: 163