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

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

Neuron 348 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: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0002

Data Index: 411050 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0745. Min Act: -0.0002

Data Index: 629075 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0720. Min Act: -0.0002

Data Index: 511639 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0667. Min Act: -0.0002

Data Index: 307064 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1060865 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0778. Min Act: -0.0002

Data Index: 766242 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0720. Min Act: -0.0002

Data Index: 802344 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0714. Min Act: -0.0002

Data Index: 313379 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0728. Min Act: -0.0002

Data Index: 59626 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1236443 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1085420 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0637. Min Act: -0.0002

Data Index: 856124 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0699. Min Act: -0.0002

Data Index: 183870 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0714. Min Act: -0.0002

Data Index: 384845 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0666. Min Act: -0.0002

Data Index: 192710 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0644. Min Act: -0.0002

Data Index: 203034 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0650. Min Act: -0.0002

Data Index: 859617 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0674. Min Act: -0.0002

Data Index: 101054 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0645. Min Act: -0.0002

Data Index: 190334 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0639. Min Act: -0.0002

Data Index: 713227 (C4 (Web Text))

Max Activating Token Index: 290