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

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

Neuron 3995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2840. Min Act: -0.0000

Data Index: 1026896 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.9245. Min Act: -0.0000

Data Index: 1559373 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.8981. Min Act: -0.0000

Data Index: 295825 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.9385. Min Act: -0.0001

Data Index: 329034 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7767. Min Act: -0.0000

Data Index: 374601 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7345. Min Act: -0.0000

Data Index: 497385 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.8017. Min Act: -0.0000

Data Index: 1107984 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7946. Min Act: -0.0000

Data Index: 473450 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.6639. Min Act: -0.0000

Data Index: 434171 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.6353. Min Act: -0.0000

Data Index: 1643076 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7897. Min Act: -0.0001

Data Index: 1411257 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.6614. Min Act: -0.0001

Data Index: 1576648 (Python Code)

Max Activating Token Index: 168

Text #12

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7829. Min Act: -0.0000

Data Index: 1439808 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.9228. Min Act: -0.0001

Data Index: 1361898 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7848. Min Act: -0.0001

Data Index: 1556746 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7996. Min Act: -0.0001

Data Index: 1441081 (Python Code)

Max Activating Token Index: 234

Text #16

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.6568. Min Act: -0.0001

Data Index: 1418306 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.6261. Min Act: -0.0000

Data Index: 1591909 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.5075. Min Act: -0.0000

Data Index: 600338 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 3.2840. Min Range: -3.2840

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1512213 (Python Code)

Max Activating Token Index: 227