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

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

Neuron 488 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.8225. Min Act: -0.0001

Data Index: 822433 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7363. Min Act: -0.0001

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6607. Min Act: -0.0001

Data Index: 441726 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6718. Min Act: -0.0001

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6731. Min Act: -0.0000

Data Index: 952593 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6546. Min Act: -0.0001

Data Index: 478881 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6733. Min Act: -0.0001

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.7077. Min Act: -0.0001

Data Index: 908479 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6482. Min Act: -0.0001

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5983. Min Act: -0.0001

Data Index: 211519 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5857. Min Act: -0.0001

Data Index: 1246350 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5927. Min Act: -0.0000

Data Index: 135694 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6197. Min Act: -0.0001

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6390. Min Act: -0.0001

Data Index: 928188 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6601. Min Act: -0.0001

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1241424 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6262. Min Act: -0.0001

Data Index: 316269 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6560. Min Act: -0.0001

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.5846. Min Act: -0.0001

Data Index: 1062835 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.8225. Min Range: -0.8225

Max Act: 0.6061. Min Act: -0.0001

Data Index: 2660 (C4 (Web Text))

Max Activating Token Index: 787