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

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

Neuron 3867 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5917. Min Range: -5.5917

Max Act: 5.5917. Min Act: -0.0001

Data Index: 170789 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 5.5917. Min Range: -5.5917

Max Act: 5.2974. Min Act: -0.0001

Data Index: 813070 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.4393. Min Act: -0.0001

Data Index: 1031724 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.2652. Min Act: -0.0001

Data Index: 798876 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.7509. Min Act: -0.0001

Data Index: 1067188 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.5378. Min Act: -0.0001

Data Index: 778067 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.9602. Min Act: -0.0001

Data Index: 282137 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.0450. Min Act: -0.0001

Data Index: 513288 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.6888. Min Act: -0.0001

Data Index: 118367 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.8222. Min Act: -0.0001

Data Index: 1133442 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.1424. Min Act: -0.0001

Data Index: 1223395 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.7443. Min Act: -0.0001

Data Index: 737000 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.2987. Min Act: -0.0001

Data Index: 816387 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.7630. Min Act: -0.0001

Data Index: 1256296 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.5835. Min Act: -0.0001

Data Index: 160024 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 5.5917. Min Range: -5.5917

Max Act: 4.0141. Min Act: -0.0001

Data Index: 132377 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.6816. Min Act: -0.0001

Data Index: 1206990 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.9659. Min Act: -0.0001

Data Index: 19611 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.8020. Min Act: -0.0001

Data Index: 829239 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 5.5917. Min Range: -5.5917

Max Act: 3.7738. Min Act: -0.0001

Data Index: 494846 (C4 (Web Text))

Max Activating Token Index: 107