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

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

Neuron 3430 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.6829. Min Act: -0.0000

Data Index: 292896 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.9700. Min Act: -0.0000

Data Index: 634968 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8980. Min Act: -0.0000

Data Index: 564329 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.4649. Min Act: -0.0000

Data Index: 375142 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.0085. Min Act: -0.0000

Data Index: 261295 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.6829. Min Range: -3.6829

Max Act: 3.0040. Min Act: -0.0000

Data Index: 926039 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.7671. Min Act: -0.0000

Data Index: 1345733 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6336. Min Act: -0.0000

Data Index: 1257775 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8900. Min Act: -0.0000

Data Index: 883220 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.5678. Min Act: -0.0000

Data Index: 385729 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.8448. Min Act: -0.0000

Data Index: 820920 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6946. Min Act: -0.0000

Data Index: 289333 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6721. Min Act: -0.0000

Data Index: 1277128 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.5421. Min Act: -0.0000

Data Index: 919032 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6770. Min Act: -0.0000

Data Index: 1287828 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6558. Min Act: -0.0000

Data Index: 988223 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.6589. Min Act: -0.0000

Data Index: 832709 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.7284. Min Act: -0.0000

Data Index: 580494 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1060284 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 3.6829. Min Range: -3.6829

Max Act: 2.5726. Min Act: -0.0000

Data Index: 1303743 (C4 (Web Text))

Max Activating Token Index: 236