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

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

Neuron 5339 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8558. Min Range: -2.8558

Max Act: 2.8558. Min Act: -0.0000

Data Index: 624844 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 2.8558. Min Range: -2.8558

Max Act: 2.2721. Min Act: -0.0000

Data Index: 81684 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 2.8558. Min Range: -2.8558

Max Act: 2.2069. Min Act: -0.0000

Data Index: 511793 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 2.8558. Min Range: -2.8558

Max Act: 2.0433. Min Act: -0.0000

Data Index: 1206148 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 2.8558. Min Range: -2.8558

Max Act: 2.0320. Min Act: -0.0000

Data Index: 499637 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.9788. Min Act: -0.0000

Data Index: 620924 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8487. Min Act: -0.0000

Data Index: 951551 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.9292. Min Act: -0.0000

Data Index: 272233 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.9107. Min Act: -0.0000

Data Index: 114660 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8700. Min Act: -0.0000

Data Index: 1152476 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8651. Min Act: -0.0000

Data Index: 1090566 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8686. Min Act: -0.0000

Data Index: 289369 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8537. Min Act: -0.0000

Data Index: 1168048 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8483. Min Act: -0.0000

Data Index: 25443 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.7103. Min Act: -0.0000

Data Index: 24817 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8066. Min Act: -0.0000

Data Index: 434869 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.9063. Min Act: -0.0000

Data Index: 835061 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.8848. Min Act: -0.0000

Data Index: 766788 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 2.8558. Min Range: -2.8558

Max Act: 1.6862. Min Act: -0.0000

Data Index: 708114 (C4 (Web Text))

Max Activating Token Index: 345