Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1122666 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0905. Min Act: -0.0003

Data Index: 1338823 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0787. Min Act: -0.0003

Data Index: 489819 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0756. Min Act: -0.0004

Data Index: 544263 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0746. Min Act: -0.0003

Data Index: 265454 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0760. Min Act: -0.0004

Data Index: 749334 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1353629 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0673. Min Act: -0.0003

Data Index: 760109 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0663. Min Act: -0.0003

Data Index: 526661 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0670. Min Act: -0.0004

Data Index: 1177974 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0656. Min Act: -0.0003

Data Index: 70131 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0652. Min Act: -0.0003

Data Index: 60296 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1180294 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0617. Min Act: -0.0003

Data Index: 627606 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0664. Min Act: -0.0004

Data Index: 1071349 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1310066 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0607. Min Act: -0.0003

Data Index: 293111 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0637. Min Act: -0.0004

Data Index: 250853 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0633. Min Act: -0.0003

Data Index: 914174 (C4 (Web Text))

Max Activating Token Index: 68