Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4467 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1628081 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.1579. Min Act: -0.0000

Data Index: 775507 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.1928. Min Act: -0.0000

Data Index: 256491 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0141. Min Act: -0.0000

Data Index: 671684 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1483185 (Python Code)

Max Activating Token Index: 716

Text #5

Max Range: 1.4924. Min Range: -1.4924

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1109924 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.4924. Min Range: -1.4924

Max Act: 0.9592. Min Act: -0.0000

Data Index: 607757 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0826. Min Act: -0.0000

Data Index: 927172 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0325. Min Act: -0.0000

Data Index: 192979 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0910. Min Act: -0.0000

Data Index: 458734 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0716. Min Act: -0.0000

Data Index: 669450 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0516. Min Act: -0.0000

Data Index: 178919 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1430496 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0473. Min Act: -0.0000

Data Index: 510806 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 1.4924. Min Range: -1.4924

Max Act: 0.9756. Min Act: -0.0000

Data Index: 777276 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0647. Min Act: -0.0000

Data Index: 32309 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1246714 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1095141 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0092. Min Act: -0.0000

Data Index: 94510 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.4924. Min Range: -1.4924

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1462750 (Python Code)

Max Activating Token Index: 816