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

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

Neuron 1646 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: 1.7909. Min Range: -1.7909

Max Act: 1.7909. Min Act: -0.0000

Data Index: 1256629 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.7909. Min Range: -1.7909

Max Act: 1.6891. Min Act: -0.0000

Data Index: 303211 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.7909. Min Range: -1.7909

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1012696 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.7909. Min Range: -1.7909

Max Act: 1.1868. Min Act: -0.0000

Data Index: 521367 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.7909. Min Range: -1.7909

Max Act: 1.1365. Min Act: -0.0000

Data Index: 17693 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 1.7909. Min Range: -1.7909

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1346034 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1152822 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.8719. Min Act: -0.0000

Data Index: 311301 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1057201 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.8780. Min Act: -0.0000

Data Index: 497079 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.8511. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1201648 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7706. Min Act: -0.0000

Data Index: 604678 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7528. Min Act: -0.0000

Data Index: 629585 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1473930 (Python Code)

Max Activating Token Index: 201

Text #15

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1072898 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7043. Min Act: -0.0000

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7547. Min Act: -0.0000

Data Index: 336292 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.6970. Min Act: -0.0000

Data Index: 53421 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.7909. Min Range: -1.7909

Max Act: 0.7881. Min Act: -0.0000

Data Index: 110363 (C4 (Web Text))

Max Activating Token Index: 633