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

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

Neuron 2893 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.5518. Min Act: -0.0000

Data Index: 706447 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1655571 (Python Code)

Max Activating Token Index: 791

Text #2

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.2295. Min Act: -0.0000

Data Index: 1465506 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.9988. Min Act: -0.0000

Data Index: 1562665 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.1351. Min Act: -0.0000

Data Index: 952293 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1441077 (Python Code)

Max Activating Token Index: 537

Text #6

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1655623 (Python Code)

Max Activating Token Index: 554

Text #7

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.1504. Min Act: -0.0000

Data Index: 597295 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8907. Min Act: -0.0000

Data Index: 1368718 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.1068. Min Act: -0.0000

Data Index: 1366837 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8673. Min Act: -0.0000

Data Index: 1566314 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 2.5518. Min Range: -2.5518

Max Act: 2.1473. Min Act: -0.0000

Data Index: 1429952 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.7188. Min Act: -0.0000

Data Index: 514982 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1507297 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1566207 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1559042 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8488. Min Act: -0.0000

Data Index: 1583626 (Python Code)

Max Activating Token Index: 743

Text #17

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8106. Min Act: -0.0000

Data Index: 1136924 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8962. Min Act: -0.0000

Data Index: 1527520 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 2.5518. Min Range: -2.5518

Max Act: 1.8997. Min Act: -0.0000

Data Index: 1613400 (Python Code)

Max Activating Token Index: 437