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

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

Neuron 105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5455. Min Act: -0.0003

Data Index: 681979 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5677. Min Act: -0.0003

Data Index: 544666 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5445. Min Act: -0.0003

Data Index: 458160 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5128. Min Act: -0.0003

Data Index: 717429 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5487. Min Act: -0.0003

Data Index: 733443 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5265. Min Act: -0.0003

Data Index: 1356450 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5193. Min Act: -0.0003

Data Index: 794331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4963. Min Act: -0.0003

Data Index: 1047948 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5040. Min Act: -0.0003

Data Index: 26884 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5049. Min Act: -0.0003

Data Index: 181451 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4998. Min Act: -0.0003

Data Index: 458193 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4943. Min Act: -0.0003

Data Index: 314180 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4912. Min Act: -0.0003

Data Index: 840618 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4872. Min Act: -0.0003

Data Index: 436438 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4824. Min Act: -0.0003

Data Index: 1045752 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4638. Min Act: -0.0003

Data Index: 108650 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4630. Min Act: -0.0003

Data Index: 743725 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4611. Min Act: -0.0003

Data Index: 741702 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4763. Min Act: -0.0003

Data Index: 431976 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4258. Min Act: -0.0003

Data Index: 1256342 (C4 (Web Text))

Max Activating Token Index: 860