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

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

Neuron 1853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.8486. Min Act: -0.0000

Data Index: 74784 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1194058 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1132367 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.6438. Min Act: -0.0000

Data Index: 522007 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4806. Min Act: -0.0000

Data Index: 894847 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.4497. Min Act: -0.0000

Data Index: 889483 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3861. Min Act: -0.0000

Data Index: 665822 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1076720 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3418. Min Act: -0.0000

Data Index: 75473 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3432. Min Act: -0.0000

Data Index: 840754 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3683. Min Act: -0.0000

Data Index: 320811 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3171. Min Act: -0.0000

Data Index: 204330 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3055. Min Act: -0.0000

Data Index: 302524 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3117. Min Act: -0.0000

Data Index: 44765 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1291068 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.2032. Min Act: -0.0000

Data Index: 677355 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1233019 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1332845 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1128675 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.8486. Min Range: -1.8486

Max Act: 1.1933. Min Act: -0.0000

Data Index: 919292 (C4 (Web Text))

Max Activating Token Index: 98