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

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

Neuron 4400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.6777. Min Act: -0.0000

Data Index: 806186 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4477. Min Act: -0.0000

Data Index: 523710 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1040329 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3854. Min Act: -0.0000

Data Index: 718920 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4379. Min Act: -0.0000

Data Index: 1323612 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4109. Min Act: -0.0000

Data Index: 1160146 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3621. Min Act: -0.0000

Data Index: 118415 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.4261. Min Act: -0.0000

Data Index: 1134570 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3726. Min Act: -0.0000

Data Index: 565749 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3285. Min Act: -0.0000

Data Index: 480668 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3680. Min Act: -0.0000

Data Index: 266767 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2871. Min Act: -0.0000

Data Index: 217698 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3334. Min Act: -0.0000

Data Index: 319173 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1165965 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2733. Min Act: -0.0000

Data Index: 934567 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2700. Min Act: -0.0000

Data Index: 748386 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2566. Min Act: -0.0000

Data Index: 260904 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.3374. Min Act: -0.0000

Data Index: 948256 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2764. Min Act: -0.0000

Data Index: 725261 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.6777. Min Range: -1.6777

Max Act: 1.2667. Min Act: -0.0000

Data Index: 422150 (C4 (Web Text))

Max Activating Token Index: 511