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

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

Neuron 3319 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: 0.0865. Min Range: -0.0865

Max Act: 0.0861. Min Act: -0.0000

Data Index: 234107 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0000

Data Index: 160882 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0837. Min Act: -0.0000

Data Index: 526593 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0781. Min Act: -0.0000

Data Index: 348282 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0805. Min Act: -0.0000

Data Index: 614521 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0776. Min Act: -0.0000

Data Index: 769724 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0753. Min Act: -0.0000

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0809. Min Act: -0.0000

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1309259 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0718. Min Act: -0.0000

Data Index: 496697 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0720. Min Act: -0.0000

Data Index: 561138 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0718. Min Act: -0.0000

Data Index: 346158 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0656. Min Act: -0.0000

Data Index: 180627 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0682. Min Act: -0.0000

Data Index: 479281 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0708. Min Act: -0.0000

Data Index: 555205 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0714. Min Act: -0.0000

Data Index: 350017 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0704. Min Act: -0.0000

Data Index: 204672 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0744. Min Act: -0.0000

Data Index: 476530 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0687. Min Act: -0.0000

Data Index: 186916 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0709. Min Act: -0.0000

Data Index: 929693 (C4 (Web Text))

Max Activating Token Index: 535