Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1050 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9998. Min Act: -0.0001

Data Index: 154211 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9873. Min Act: -0.0000

Data Index: 43045 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9585. Min Act: -0.0001

Data Index: 297044 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8767. Min Act: -0.0000

Data Index: 660009 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9632. Min Act: -0.0000

Data Index: 590723 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9829. Min Act: -0.0000

Data Index: 857471 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9477. Min Act: -0.0001

Data Index: 646349 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9200. Min Act: -0.0000

Data Index: 901860 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8890. Min Act: -0.0001

Data Index: 857686 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.9546. Min Act: -0.0001

Data Index: 716925 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8842. Min Act: -0.0001

Data Index: 1074467 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8329. Min Act: -0.0001

Data Index: 1249660 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1356590 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8602. Min Act: -0.0001

Data Index: 1268855 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8327. Min Act: -0.0001

Data Index: 36270 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8862. Min Act: -0.0001

Data Index: 306477 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8268. Min Act: -0.0000

Data Index: 285212 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8828. Min Act: -0.0001

Data Index: 888684 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8512. Min Act: -0.0000

Data Index: 71781 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.9998. Min Range: -0.9998

Max Act: 0.8193. Min Act: -0.0001

Data Index: 117113 (C4 (Web Text))

Max Activating Token Index: 42