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

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

Neuron 218 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: 6.4488. Min Range: -6.4488

Max Act: 6.3161. Min Act: -0.0000

Data Index: 827716 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 6.4488. Min Range: -6.4488

Max Act: 6.4488. Min Act: -0.0000

Data Index: 41460 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.7712. Min Act: -0.0000

Data Index: 1096931 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.9141. Min Act: -0.0000

Data Index: 1024648 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.6855. Min Act: -0.0000

Data Index: 834842 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.3669. Min Act: -0.0000

Data Index: 1241663 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.3756. Min Act: -0.0000

Data Index: 489837 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.3462. Min Act: -0.0000

Data Index: 40494 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.5258. Min Act: -0.0000

Data Index: 437582 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.0783. Min Act: -0.0000

Data Index: 675825 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.3579. Min Act: -0.0000

Data Index: 465552 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.1823. Min Act: -0.0000

Data Index: 752209 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 6.4488. Min Range: -6.4488

Max Act: 4.8945. Min Act: -0.0000

Data Index: 382085 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.0603. Min Act: -0.0000

Data Index: 988143 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.0117. Min Act: -0.0000

Data Index: 400434 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 6.4488. Min Range: -6.4488

Max Act: 4.8118. Min Act: -0.0000

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 6.4488. Min Range: -6.4488

Max Act: 5.3276. Min Act: -0.0000

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 6.4488. Min Range: -6.4488

Max Act: 4.9811. Min Act: -0.0000

Data Index: 1181657 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 6.4488. Min Range: -6.4488

Max Act: 4.7927. Min Act: -0.0000

Data Index: 844163 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 6.4488. Min Range: -6.4488

Max Act: 4.7770. Min Act: -0.0000

Data Index: 940747 (C4 (Web Text))

Max Activating Token Index: 405