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

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

Neuron 766 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.5020. Min Act: -0.0000

Data Index: 245417 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.4132. Min Act: -0.0000

Data Index: 919771 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3739. Min Act: -0.0000

Data Index: 245213 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1134059 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3612. Min Act: -0.0000

Data Index: 185306 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3598. Min Act: -0.0000

Data Index: 13736 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3582. Min Act: -0.0000

Data Index: 797288 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3398. Min Act: -0.0000

Data Index: 754676 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2919. Min Act: -0.0000

Data Index: 868166 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 858352 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2915. Min Act: -0.0000

Data Index: 438908 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2953. Min Act: -0.0000

Data Index: 344994 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2827. Min Act: -0.0000

Data Index: 628752 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1020535 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2835. Min Act: -0.0000

Data Index: 525444 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2728. Min Act: 0.0001

Data Index: 1136934 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2720. Min Act: -0.0000

Data Index: 60004 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2529. Min Act: 0.0000

Data Index: 237033 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2508. Min Act: -0.0000

Data Index: 778805 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.5020. Min Range: -0.5020

Max Act: 0.2561. Min Act: -0.0000

Data Index: 632817 (C4 (Web Text))

Max Activating Token Index: 650