Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9728. Min Act: -0.0000

Data Index: 531914 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7782. Min Act: -0.0000

Data Index: 46104 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7722. Min Act: -0.0000

Data Index: 875795 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7296. Min Act: -0.0000

Data Index: 94112 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.7178. Min Act: -0.0000

Data Index: 452775 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6923. Min Act: -0.0000

Data Index: 65019 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6593. Min Act: -0.0000

Data Index: 456543 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1299841 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6209. Min Act: -0.0000

Data Index: 837193 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1323039 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5655. Min Act: -0.0000

Data Index: 572818 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5994. Min Act: -0.0000

Data Index: 189000 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6077. Min Act: -0.0000

Data Index: 580101 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1072760 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6104. Min Act: -0.0000

Data Index: 149064 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.6110. Min Act: -0.0000

Data Index: 881348 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1220861 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5804. Min Act: -0.0000

Data Index: 201622 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1232437 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.5988. Min Act: -0.0000

Data Index: 464749 (C4 (Web Text))

Max Activating Token Index: 1001