Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2970 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.5041. Min Act: -0.0001

Data Index: 226496 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.5540. Min Act: -0.0001

Data Index: 292163 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.4623. Min Act: -0.0001

Data Index: 1101085 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.4595. Min Act: -0.0001

Data Index: 680392 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2941. Min Act: -0.0001

Data Index: 322032 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.3692. Min Act: -0.0001

Data Index: 103493 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.4591. Min Act: -0.0001

Data Index: 299781 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.4296. Min Act: -0.0001

Data Index: 174377 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.4246. Min Act: -0.0001

Data Index: 549127 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.3367. Min Act: -0.0001

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2178. Min Act: -0.0001

Data Index: 294580 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2491. Min Act: -0.0001

Data Index: 391426 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2070. Min Act: -0.0001

Data Index: 82659 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2312. Min Act: -0.0001

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2893. Min Act: -0.0001

Data Index: 994580 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2020. Min Act: -0.0001

Data Index: 177600 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.1957. Min Act: -0.0001

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.1271. Min Act: -0.0001

Data Index: 715776 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.1757. Min Act: -0.0001

Data Index: 759786 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.5540. Min Range: -1.5540

Max Act: 1.2353. Min Act: -0.0001

Data Index: 2211 (C4 (Web Text))

Max Activating Token Index: 168