Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1773 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.6301. Min Act: -0.0001

Data Index: 128716 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5374. Min Act: -0.0001

Data Index: 460246 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5431. Min Act: -0.0001

Data Index: 1047349 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5241. Min Act: -0.0001

Data Index: 708869 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1050414 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5212. Min Act: -0.0001

Data Index: 1150029 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5506. Min Act: -0.0001

Data Index: 111572 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5304. Min Act: -0.0001

Data Index: 403970 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5417. Min Act: -0.0001

Data Index: 1324853 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.5017. Min Act: -0.0001

Data Index: 2345 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4335. Min Act: -0.0001

Data Index: 982094 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4814. Min Act: -0.0001

Data Index: 400552 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4646. Min Act: -0.0001

Data Index: 780073 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4619. Min Act: -0.0001

Data Index: 199983 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4816. Min Act: -0.0001

Data Index: 115464 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4750. Min Act: -0.0001

Data Index: 871920 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4585. Min Act: -0.0001

Data Index: 58129 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4246. Min Act: -0.0001

Data Index: 850687 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4536. Min Act: -0.0001

Data Index: 120242 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.6301. Min Range: -0.6301

Max Act: 0.4682. Min Act: -0.0001

Data Index: 785913 (C4 (Web Text))

Max Activating Token Index: 943