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

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

Neuron 1283 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: 1.9102. Min Range: -1.9102

Max Act: 1.9102. Min Act: -0.0000

Data Index: 611946 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.8732. Min Act: -0.0000

Data Index: 926104 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.8662. Min Act: -0.0000

Data Index: 602556 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.6098. Min Act: -0.0000

Data Index: 316777 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4207. Min Act: -0.0000

Data Index: 327629 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.5795. Min Act: -0.0000

Data Index: 108267 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4631. Min Act: -0.0000

Data Index: 299509 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4326. Min Act: -0.0000

Data Index: 189420 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.5141. Min Act: -0.0000

Data Index: 528250 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4102. Min Act: -0.0000

Data Index: 961238 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4906. Min Act: -0.0000

Data Index: 39682 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.5520. Min Act: -0.0000

Data Index: 529973 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1192550 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1298171 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.3984. Min Act: -0.0000

Data Index: 123282 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.4751. Min Act: -0.0000

Data Index: 257504 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.3662. Min Act: -0.0000

Data Index: 479999 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.3436. Min Act: -0.0000

Data Index: 682694 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.2285. Min Act: -0.0000

Data Index: 311555 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 1.9102. Min Range: -1.9102

Max Act: 1.3789. Min Act: -0.0000

Data Index: 612472 (C4 (Web Text))

Max Activating Token Index: 27