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

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

Neuron 4825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1717. Min Act: -0.0000

Data Index: 354192 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1313. Min Act: -0.0000

Data Index: 377521 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1312020 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1277797 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1351275 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0849. Min Act: -0.0000

Data Index: 90744 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1003531 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0827. Min Act: -0.0000

Data Index: 724151 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0849. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0870. Min Act: 0.0001

Data Index: 878109 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0806. Min Act: -0.0000

Data Index: 262866 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0822. Min Act: 0.0000

Data Index: 203538 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0702. Min Act: 0.0001

Data Index: 966403 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0716. Min Act: -0.0000

Data Index: 786282 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0765. Min Act: -0.0000

Data Index: 533226 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0602. Min Act: -0.0000

Data Index: 828318 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0686. Min Act: -0.0000

Data Index: 631964 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0654. Min Act: 0.0001

Data Index: 1471014 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0605. Min Act: -0.0000

Data Index: 200772 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1034574 (C4 (Web Text))

Max Activating Token Index: 427