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

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

Neuron 2274 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: 7.8625. Min Range: -7.8625

Max Act: 7.6374. Min Act: -0.0000

Data Index: 223134 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.6801. Min Act: -0.0000

Data Index: 502447 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.8625. Min Act: -0.0000

Data Index: 296826 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.4631. Min Act: -0.0000

Data Index: 788031 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.0730. Min Act: -0.0000

Data Index: 1117125 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.7158. Min Act: -0.0000

Data Index: 1145353 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.3302. Min Act: -0.0000

Data Index: 5528 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.3228. Min Act: -0.0000

Data Index: 1016198 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.6653. Min Act: -0.0000

Data Index: 275604 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.1008. Min Act: -0.0000

Data Index: 848591 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.2797. Min Act: -0.0000

Data Index: 861303 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.2299. Min Act: -0.0000

Data Index: 912414 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.2298. Min Act: -0.0000

Data Index: 43816 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.6440. Min Act: -0.0000

Data Index: 183197 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.4544. Min Act: -0.0000

Data Index: 106981 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.1497. Min Act: -0.0000

Data Index: 567272 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.1320. Min Act: -0.0000

Data Index: 801951 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.2855. Min Act: -0.0000

Data Index: 795516 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.6626. Min Act: -0.0000

Data Index: 758801 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 7.8625. Min Range: -7.8625

Max Act: 7.2556. Min Act: -0.0000

Data Index: 1276829 (C4 (Web Text))

Max Activating Token Index: 740