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

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

Neuron 2078 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: 2.9019. Min Range: -2.9019

Max Act: 2.9019. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 2.9019. Min Range: -2.9019

Max Act: 2.8738. Min Act: -0.0000

Data Index: 1315164 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.9019. Min Range: -2.9019

Max Act: 2.7130. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 2.9019. Min Range: -2.9019

Max Act: 2.5403. Min Act: -0.0000

Data Index: 563768 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 2.9019. Min Range: -2.9019

Max Act: 2.5877. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.5876. Min Act: -0.0000

Data Index: 609206 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.5924. Min Act: -0.0000

Data Index: 709983 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.4700. Min Act: -0.0000

Data Index: 594956 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.3493. Min Act: -0.0000

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.3432. Min Act: -0.0000

Data Index: 803372 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.3064. Min Act: -0.0000

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.1900. Min Act: -0.0000

Data Index: 1312465 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2249. Min Act: -0.0000

Data Index: 455879 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2561. Min Act: -0.0000

Data Index: 151284 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2235. Min Act: -0.0000

Data Index: 833175 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1251608 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1029541 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2748. Min Act: -0.0000

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 2.9019. Min Range: -2.9019

Max Act: 1.2257. Min Act: -0.0000

Data Index: 542741 (C4 (Web Text))

Max Activating Token Index: 349