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

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

Neuron 1163 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.8623. Min Act: -0.0001

Data Index: 1143546 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.2143. Min Act: -0.0000

Data Index: 436909 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.7556. Min Act: -0.0000

Data Index: 133375 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.6133. Min Act: -0.0000

Data Index: 229959 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5870. Min Act: -0.0000

Data Index: 669533 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.4087. Min Act: -0.0001

Data Index: 457019 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5461. Min Act: -0.0000

Data Index: 434469 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3389. Min Act: -0.0000

Data Index: 1327265 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.4421. Min Act: -0.0001

Data Index: 779796 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5840. Min Act: -0.0000

Data Index: 749564 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.5359. Min Act: -0.0000

Data Index: 363965 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.4745. Min Act: -0.0000

Data Index: 1063788 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.3113. Min Act: -0.0000

Data Index: 1323519 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.0838. Min Act: -0.0001

Data Index: 183354 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.1338. Min Act: -0.0000

Data Index: 669910 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 3.8623. Min Range: -3.8623

Max Act: 1.9636. Min Act: -0.0000

Data Index: 966893 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 3.8623. Min Range: -3.8623

Max Act: 1.9759. Min Act: -0.0000

Data Index: 709935 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.0738. Min Act: -0.0000

Data Index: 2077 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.8623. Min Range: -3.8623

Max Act: 1.9448. Min Act: -0.0000

Data Index: 437751 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 3.8623. Min Range: -3.8623

Max Act: 2.0678. Min Act: -0.0000

Data Index: 486759 (C4 (Web Text))

Max Activating Token Index: 368