Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 166 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.6804. Min Act: -0.0001

Data Index: 832939 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4912. Min Act: -0.0001

Data Index: 138605 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4657. Min Act: -0.0001

Data Index: 678228 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4934. Min Act: -0.0001

Data Index: 1215341 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4404. Min Act: -0.0001

Data Index: 14135 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4215. Min Act: -0.0001

Data Index: 1013911 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4826. Min Act: -0.0001

Data Index: 1054275 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3534. Min Act: -0.0001

Data Index: 47220 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5079. Min Act: -0.0001

Data Index: 200770 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3649. Min Act: -0.0001

Data Index: 1305388 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3538. Min Act: -0.0001

Data Index: 1029988 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3916. Min Act: -0.0001

Data Index: 696855 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3563. Min Act: -0.0001

Data Index: 761435 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2850. Min Act: -0.0001

Data Index: 330611 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.5823. Min Act: -0.0001

Data Index: 768901 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4621. Min Act: -0.0001

Data Index: 795900 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3715. Min Act: -0.0001

Data Index: 862414 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2771. Min Act: -0.0001

Data Index: 233989 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2733. Min Act: -0.0001

Data Index: 853332 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2669. Min Act: -0.0001

Data Index: 500651 (C4 (Web Text))

Max Activating Token Index: 443