Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1926 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1321. Min Range: -3.1321

Max Act: 3.1321. Min Act: -0.0000

Data Index: 922037 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.8220. Min Act: 0.0000

Data Index: 61635 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.7866. Min Act: -0.0000

Data Index: 476867 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.7320. Min Act: -0.0000

Data Index: 583128 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.5005. Min Act: -0.0000

Data Index: 602670 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.4362. Min Act: -0.0000

Data Index: 180593 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.3907. Min Act: -0.0000

Data Index: 894241 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.3040. Min Act: -0.0000

Data Index: 963527 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.1640. Min Act: -0.0000

Data Index: 422682 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1332347 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.2240. Min Act: -0.0000

Data Index: 1081980 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.2194. Min Act: -0.0000

Data Index: 1329597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.2129. Min Act: 0.0000

Data Index: 239045 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1254212 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.0752. Min Act: -0.0000

Data Index: 1138413 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.1149. Min Act: -0.0000

Data Index: 826734 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.1178. Min Act: -0.0000

Data Index: 960190 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.1010. Min Act: -0.0000

Data Index: 244378 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.1321. Min Range: -3.1321

Max Act: 2.0732. Min Act: -0.0000

Data Index: 897735 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 3.1321. Min Range: -3.1321

Max Act: 1.9587. Min Act: -0.0000

Data Index: 757122 (C4 (Web Text))

Max Activating Token Index: 873