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

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

Neuron 2248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8463. Min Act: -0.0000

Data Index: 387000 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8653. Min Act: -0.0000

Data Index: 258334 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1093594 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7219. Min Act: -0.0000

Data Index: 239981 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.7528. Min Act: -0.0000

Data Index: 136592 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6756. Min Act: -0.0000

Data Index: 740552 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1087055 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6575. Min Act: -0.0000

Data Index: 812831 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6534. Min Act: -0.0000

Data Index: 943151 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6224. Min Act: -0.0000

Data Index: 866115 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5977. Min Act: -0.0000

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6029. Min Act: -0.0000

Data Index: 693702 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1002175 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5538. Min Act: -0.0001

Data Index: 93739 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6128. Min Act: -0.0000

Data Index: 743135 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5865. Min Act: -0.0000

Data Index: 665543 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1208640 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5457. Min Act: -0.0000

Data Index: 325739 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5960. Min Act: -0.0000

Data Index: 986013 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5942. Min Act: -0.0000

Data Index: 673606 (C4 (Web Text))

Max Activating Token Index: 473