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

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

Neuron 3998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1280. Min Act: -0.0000

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1287949 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1064. Min Act: -0.0000

Data Index: 854128 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0893. Min Act: -0.0000

Data Index: 892630 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0888. Min Act: -0.0000

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0794. Min Act: -0.0000

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1156659 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0730. Min Act: -0.0000

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0662. Min Act: -0.0000

Data Index: 901577 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0703. Min Act: -0.0000

Data Index: 924720 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1360490 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1294294 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0699. Min Act: -0.0000

Data Index: 526291 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1055524 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0615. Min Act: -0.0000

Data Index: 345420 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1293742 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0610. Min Act: -0.0000

Data Index: 2859 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0585. Min Act: -0.0000

Data Index: 483632 (C4 (Web Text))

Max Activating Token Index: 139