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

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

Neuron 1582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.5081. Min Act: -0.0002

Data Index: 811308 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4919. Min Act: -0.0002

Data Index: 9098 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.5277. Min Act: -0.0002

Data Index: 671760 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4757. Min Act: -0.0002

Data Index: 961548 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.5303. Min Act: -0.0002

Data Index: 462315 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4628. Min Act: -0.0002

Data Index: 250120 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4797. Min Act: -0.0002

Data Index: 1146659 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4738. Min Act: -0.0002

Data Index: 1268376 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4524. Min Act: -0.0002

Data Index: 361936 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4525. Min Act: -0.0002

Data Index: 182020 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.5102. Min Act: -0.0002

Data Index: 42184 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.3895. Min Act: -0.0002

Data Index: 275924 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4770. Min Act: -0.0002

Data Index: 620491 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4735. Min Act: -0.0002

Data Index: 375213 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4562. Min Act: -0.0002

Data Index: 941292 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4756. Min Act: -0.0002

Data Index: 899367 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4803. Min Act: -0.0002

Data Index: 45533 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4937. Min Act: -0.0002

Data Index: 966011 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4469. Min Act: -0.0002

Data Index: 1297563 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.5303. Min Range: -0.5303

Max Act: 0.4173. Min Act: -0.0002

Data Index: 915070 (C4 (Web Text))

Max Activating Token Index: 527