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

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

Neuron 5820 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: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 907022 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1027264 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7694. Min Act: -0.0000

Data Index: 928389 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7902. Min Act: -0.0000

Data Index: 172499 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1138672 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7518. Min Act: -0.0000

Data Index: 487987 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7703. Min Act: -0.0000

Data Index: 146228 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7495. Min Act: -0.0000

Data Index: 137264 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7351. Min Act: -0.0000

Data Index: 475360 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7257. Min Act: -0.0000

Data Index: 11012 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1342559 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7026. Min Act: -0.0000

Data Index: 558411 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1281432 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7143. Min Act: -0.0000

Data Index: 217742 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7161. Min Act: -0.0000

Data Index: 826208 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7160. Min Act: -0.0000

Data Index: 963698 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7121. Min Act: -0.0000

Data Index: 785751 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1341135 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6605. Min Act: -0.0000

Data Index: 166224 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1224674 (C4 (Web Text))

Max Activating Token Index: 101