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

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

Neuron 532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1148298 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5452. Min Act: -0.0000

Data Index: 452903 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.4908. Min Act: -0.0000

Data Index: 978277 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.4410. Min Act: -0.0000

Data Index: 210558 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1255300 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.3130. Min Act: -0.0000

Data Index: 578531 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.3130. Min Act: -0.0000

Data Index: 879900 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0929. Min Act: -0.0000

Data Index: 226102 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.1670. Min Act: -0.0000

Data Index: 658503 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.2298. Min Act: -0.0000

Data Index: 123598 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1300949 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1248649 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.2654. Min Act: -0.0000

Data Index: 984688 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.2777. Min Act: -0.0000

Data Index: 11634 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.1271. Min Act: -0.0000

Data Index: 643696 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1094331 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0834. Min Act: -0.0000

Data Index: 610221 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0625. Min Act: -0.0000

Data Index: 999268 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1107796 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1042064 (C4 (Web Text))

Max Activating Token Index: 629