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

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

Neuron 3057 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1752. Min Act: -0.0001

Data Index: 928446 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1768. Min Act: -0.0001

Data Index: 770238 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1761. Min Act: -0.0001

Data Index: 62946 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1797. Min Act: -0.0001

Data Index: 586477 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1257206 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1227252 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1516171 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1735. Min Act: -0.0001

Data Index: 570094 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1761. Min Act: -0.0001

Data Index: 390584 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1628. Min Act: -0.0001

Data Index: 65612 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1748. Min Act: -0.0001

Data Index: 824524 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1526. Min Act: -0.0001

Data Index: 997318 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1249940 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1572. Min Act: -0.0001

Data Index: 385050 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1624. Min Act: -0.0001

Data Index: 690911 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1614. Min Act: -0.0001

Data Index: 910342 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1527. Min Act: -0.0001

Data Index: 446717 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1726. Min Act: -0.0001

Data Index: 357611 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1499. Min Act: -0.0001

Data Index: 658340 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.1800. Min Range: -0.1800

Max Act: 0.1659. Min Act: -0.0001

Data Index: 66099 (C4 (Web Text))

Max Activating Token Index: 246