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

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

Neuron 4636 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: 2.1929. Min Range: -2.1929

Max Act: 2.1929. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 2.1929. Min Range: -2.1929

Max Act: 2.1050. Min Act: -0.0000

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.1929. Min Range: -2.1929

Max Act: 2.1283. Min Act: -0.0000

Data Index: 367186 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.8564. Min Act: -0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 2.1929. Min Range: -2.1929

Max Act: 2.0892. Min Act: -0.0000

Data Index: 847478 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7487. Min Act: -0.0000

Data Index: 701737 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.8579. Min Act: -0.0000

Data Index: 417247 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.9644. Min Act: -0.0000

Data Index: 161395 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1293956 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.8529. Min Act: -0.0000

Data Index: 877772 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.8415. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.8177. Min Act: -0.0000

Data Index: 107723 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7144. Min Act: -0.0000

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.6673. Min Act: -0.0000

Data Index: 421315 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7286. Min Act: -0.0000

Data Index: 445480 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.6612. Min Act: -0.0000

Data Index: 107235 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7440. Min Act: -0.0000

Data Index: 826501 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7545. Min Act: -0.0000

Data Index: 392521 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7934. Min Act: -0.0000

Data Index: 577171 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.1929. Min Range: -2.1929

Max Act: 1.7461. Min Act: -0.0000

Data Index: 410775 (C4 (Web Text))

Max Activating Token Index: 481