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

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

Neuron 2327 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.8563. Min Act: -0.0000

Data Index: 695912 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.3602. Min Act: -0.0000

Data Index: 281499 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.2856. Min Act: -0.0000

Data Index: 45166 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.0957. Min Act: -0.0000

Data Index: 344444 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.8563. Min Range: -2.8563

Max Act: 2.0898. Min Act: -0.0000

Data Index: 1457230 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.8510. Min Act: -0.0000

Data Index: 1104328 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.8841. Min Act: -0.0000

Data Index: 972611 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.8726. Min Act: -0.0000

Data Index: 1210671 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.7528. Min Act: -0.0000

Data Index: 1270421 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.9493. Min Act: -0.0000

Data Index: 1325279 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.8024. Min Act: -0.0000

Data Index: 564585 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.8809. Min Act: -0.0000

Data Index: 180745 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.7256. Min Act: -0.0000

Data Index: 336414 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.5952. Min Act: -0.0000

Data Index: 286854 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.6885. Min Act: -0.0000

Data Index: 415360 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1010460 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.5448. Min Act: -0.0000

Data Index: 166154 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.6116. Min Act: -0.0000

Data Index: 499549 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.5774. Min Act: -0.0000

Data Index: 21393 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 2.8563. Min Range: -2.8563

Max Act: 1.5666. Min Act: -0.0000

Data Index: 934191 (C4 (Web Text))

Max Activating Token Index: 755