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

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

Neuron 2815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0001

Data Index: 44014 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0626. Min Act: -0.0000

Data Index: 312581 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0610. Min Act: -0.0001

Data Index: 193503 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0614. Min Act: -0.0001

Data Index: 298007 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0632. Min Act: -0.0000

Data Index: 381623 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0583. Min Act: -0.0000

Data Index: 974435 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1194860 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0553. Min Act: -0.0000

Data Index: 702268 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1328976 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0560. Min Act: -0.0000

Data Index: 767314 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0552. Min Act: -0.0000

Data Index: 5992 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1056819 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0562. Min Act: -0.0000

Data Index: 926128 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0551. Min Act: -0.0000

Data Index: 417800 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1194244 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0535. Min Act: -0.0000

Data Index: 321465 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0550. Min Act: -0.0001

Data Index: 375957 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1594798 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0531. Min Act: -0.0000

Data Index: 861577 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1378595 (Python Code)

Max Activating Token Index: 127