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

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

Neuron 1532 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1546635 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0977. Min Act: -0.0002

Data Index: 36632 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1605560 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1388434 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1545055 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1383928 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1514672 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1490572 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1564632 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1013997 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1432419 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1623607 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1627914 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1389535 (Python Code)

Max Activating Token Index: 527

Text #14

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0911. Min Act: -0.0002

Data Index: 769432 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1418211 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0889. Min Act: -0.0002

Data Index: 614039 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1590010 (Python Code)

Max Activating Token Index: 137

Text #18

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1497757 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.0999. Min Range: -0.0999

Max Act: 0.0886. Min Act: -0.0002

Data Index: 133137 (C4 (Web Text))

Max Activating Token Index: 235