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

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

Neuron 2164 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1595732 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.4586. Min Act: -0.0000

Data Index: 1418013 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.4379. Min Act: -0.0000

Data Index: 1529184 (Python Code)

Max Activating Token Index: 957

Text #3

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.3034. Min Act: -0.0000

Data Index: 1538268 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1449375 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.3241. Min Act: -0.0000

Data Index: 1470764 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.3485. Min Act: -0.0000

Data Index: 1527080 (Python Code)

Max Activating Token Index: 891

Text #7

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.1849. Min Act: -0.0000

Data Index: 1466209 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.3107. Min Act: -0.0000

Data Index: 1631245 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.3084. Min Act: -0.0000

Data Index: 1511078 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.5349. Min Act: -0.0000

Data Index: 1535621 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.2492. Min Act: -0.0000

Data Index: 1592128 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.2273. Min Act: -0.0000

Data Index: 1455546 (Python Code)

Max Activating Token Index: 568

Text #13

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1509638 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1545321 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.0308. Min Act: -0.0000

Data Index: 1414527 (Python Code)

Max Activating Token Index: 894

Text #16

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.1380. Min Act: -0.0000

Data Index: 1411550 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1597162 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1462561 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 2.5841. Min Range: -2.5841

Max Act: 2.0463. Min Act: -0.0000

Data Index: 1561078 (Python Code)

Max Activating Token Index: 436