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

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

Neuron 1157 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0001

Data Index: 997849 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5640. Min Act: -0.0001

Data Index: 977632 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5495. Min Act: -0.0001

Data Index: 1294491 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5719. Min Act: -0.0001

Data Index: 500915 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1157657 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4650. Min Act: -0.0001

Data Index: 777354 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4918. Min Act: -0.0001

Data Index: 705200 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5299. Min Act: -0.0001

Data Index: 728176 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5300. Min Act: -0.0001

Data Index: 967169 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5747. Min Act: -0.0001

Data Index: 1318943 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5135. Min Act: -0.0001

Data Index: 932465 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4793. Min Act: -0.0001

Data Index: 364632 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4936. Min Act: -0.0001

Data Index: 369288 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4888. Min Act: -0.0001

Data Index: 1325355 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1120819 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5585. Min Act: -0.0001

Data Index: 225090 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4949. Min Act: -0.0001

Data Index: 632683 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4557. Min Act: -0.0001

Data Index: 178870 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4638. Min Act: -0.0001

Data Index: 1059567 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5142. Min Act: -0.0001

Data Index: 889133 (C4 (Web Text))

Max Activating Token Index: 522