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

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

Neuron 1243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1179767 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7603. Min Act: -0.0000

Data Index: 361058 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7353. Min Act: -0.0000

Data Index: 408215 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7421. Min Act: -0.0000

Data Index: 102845 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7460. Min Act: -0.0000

Data Index: 582275 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1097095 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1200144 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.7026. Min Act: -0.0000

Data Index: 210671 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1257731 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6828. Min Act: -0.0000

Data Index: 660268 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1197280 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6536. Min Act: -0.0000

Data Index: 198209 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6876. Min Act: -0.0000

Data Index: 994524 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1082972 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6387. Min Act: -0.0000

Data Index: 971000 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6158. Min Act: -0.0000

Data Index: 498782 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1122454 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6072. Min Act: -0.0000

Data Index: 150496 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6547. Min Act: -0.0000

Data Index: 515587 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.7766. Min Range: -0.7766

Max Act: 0.6482. Min Act: -0.0000

Data Index: 966177 (C4 (Web Text))

Max Activating Token Index: 271