Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 473 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.5526. Min Act: -0.0001

Data Index: 652320 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1298. Min Act: -0.0001

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.1033. Min Act: -0.0001

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0427. Min Act: -0.0001

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 1.5526. Min Range: -1.5526

Max Act: 1.0187. Min Act: -0.0001

Data Index: 366780 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9403. Min Act: -0.0001

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9350. Min Act: -0.0001

Data Index: 861799 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9500. Min Act: -0.0001

Data Index: 1067424 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9885. Min Act: -0.0001

Data Index: 384290 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8946. Min Act: -0.0001

Data Index: 1254103 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9265. Min Act: -0.0001

Data Index: 372324 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8898. Min Act: -0.0001

Data Index: 1264565 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8525. Min Act: -0.0001

Data Index: 912068 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8617. Min Act: -0.0001

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.9264. Min Act: -0.0001

Data Index: 440275 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8933. Min Act: -0.0001

Data Index: 687133 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8120. Min Act: -0.0001

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.7640. Min Act: -0.0001

Data Index: 414822 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1269298 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.5526. Min Range: -1.5526

Max Act: 0.7656. Min Act: -0.0001

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 455