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

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

Neuron 795 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0712. Min Act: -0.0001

Data Index: 963503 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0648. Min Act: -0.0001

Data Index: 570528 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0000

Data Index: 338618 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0673. Min Act: -0.0000

Data Index: 791477 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1319216 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1223127 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0642. Min Act: -0.0000

Data Index: 897044 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0573. Min Act: -0.0001

Data Index: 888541 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0565. Min Act: -0.0001

Data Index: 699860 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1010319 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1045456 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0487. Min Act: -0.0000

Data Index: 16046 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0539. Min Act: -0.0001

Data Index: 894559 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0542. Min Act: -0.0000

Data Index: 8353 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0463. Min Act: -0.0001

Data Index: 10120 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0555. Min Act: -0.0000

Data Index: 78348 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1043315 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0535. Min Act: -0.0000

Data Index: 789219 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0538. Min Act: -0.0000

Data Index: 918157 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0524. Min Act: -0.0000

Data Index: 101954 (C4 (Web Text))

Max Activating Token Index: 672