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

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

Neuron 1572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.4686. Min Act: -0.0000

Data Index: 427003 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.4270. Min Act: -0.0000

Data Index: 363467 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2529. Min Act: -0.0000

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2132. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1182913 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.2682. Min Act: -0.0000

Data Index: 926663 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.1063. Min Act: -0.0000

Data Index: 669707 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0897. Min Act: -0.0000

Data Index: 886530 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1220645 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1296369 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0898. Min Act: -0.0000

Data Index: 339877 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0260. Min Act: -0.0000

Data Index: 790674 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.1546. Min Act: -0.0000

Data Index: 500132 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.1012. Min Act: -0.0000

Data Index: 1277916 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.4686. Min Range: -1.4686

Max Act: 1.0159. Min Act: -0.0000

Data Index: 317511 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.4686. Min Range: -1.4686

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1282694 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.4686. Min Range: -1.4686

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1031924 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 1.4686. Min Range: -1.4686

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1009569 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.4686. Min Range: -1.4686

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1152789 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.4686. Min Range: -1.4686

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1173993 (C4 (Web Text))

Max Activating Token Index: 178