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

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

Neuron 621 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.4500. Min Act: -0.0000

Data Index: 997504 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.4446. Min Act: -0.0000

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.4517. Min Act: -0.0000

Data Index: 36215 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.4522. Min Act: -0.0000

Data Index: 827192 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.2974. Min Act: -0.0000

Data Index: 624540 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.3254. Min Act: -0.0000

Data Index: 959269 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.3102. Min Act: -0.0000

Data Index: 670384 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.1403. Min Act: -0.0000

Data Index: 1161340 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.1202. Min Act: -0.0000

Data Index: 1043026 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.2488. Min Act: -0.0000

Data Index: 564161 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.1014. Min Act: -0.0000

Data Index: 592040 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 2.4522. Min Range: -2.4522

Max Act: 2.0013. Min Act: -0.0000

Data Index: 958476 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 2.4522. Min Range: -2.4522

Max Act: 1.3338. Min Act: -0.0000

Data Index: 72303 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1069086 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.9475. Min Act: -0.0000

Data Index: 134801 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.9228. Min Act: -0.0000

Data Index: 684543 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.8455. Min Act: -0.0000

Data Index: 743902 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1016161 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1224122 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 2.4522. Min Range: -2.4522

Max Act: 0.8534. Min Act: -0.0000

Data Index: 263482 (C4 (Web Text))

Max Activating Token Index: 52