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

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

Neuron 13 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1391859 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1095236 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5697. Min Act: -0.0001

Data Index: 1528155 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4946. Min Act: -0.0001

Data Index: 1502890 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4899. Min Act: -0.0001

Data Index: 188397 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1589476 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4683. Min Act: -0.0000

Data Index: 1646060 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4859. Min Act: -0.0001

Data Index: 118652 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1224259 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1403970 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1094002 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1420212 (Python Code)

Max Activating Token Index: 99

Text #12

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4483. Min Act: -0.0001

Data Index: 1450650 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4742. Min Act: -0.0001

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1434393 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1441892 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4766. Min Act: -0.0001

Data Index: 822122 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1420690 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1429587 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.5697. Min Range: -0.5697

Max Act: 0.4761. Min Act: -0.0001

Data Index: 906189 (C4 (Web Text))

Max Activating Token Index: 620