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

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

Neuron 3005 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.1398. Min Act: -0.0000

Data Index: 209954 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.0839. Min Act: -0.0000

Data Index: 667156 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9842. Min Act: -0.0000

Data Index: 289232 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.0866. Min Act: -0.0000

Data Index: 423860 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9347. Min Act: -0.0000

Data Index: 373622 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.1398. Min Range: -1.1398

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8529. Min Act: -0.0000

Data Index: 48936 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9213. Min Act: -0.0000

Data Index: 536609 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9338. Min Act: -0.0000

Data Index: 113264 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9620. Min Act: -0.0000

Data Index: 58678 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9614. Min Act: -0.0000

Data Index: 154615 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1188892 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8937. Min Act: -0.0000

Data Index: 600880 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.9475. Min Act: -0.0000

Data Index: 163784 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8855. Min Act: -0.0000

Data Index: 545991 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8667. Min Act: -0.0000

Data Index: 480196 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8829. Min Act: -0.0000

Data Index: 987818 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1276655 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.1398. Min Range: -1.1398

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1206908 (C4 (Web Text))

Max Activating Token Index: 887