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

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

Neuron 2453 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.6391. Min Act: -0.0001

Data Index: 826538 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.0753. Min Act: -0.0001

Data Index: 180298 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.0429. Min Act: -0.0001

Data Index: 241850 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.4384. Min Act: -0.0001

Data Index: 804524 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.1861. Min Act: -0.0001

Data Index: 508133 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.2936. Min Act: -0.0001

Data Index: 228129 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.2138. Min Act: -0.0001

Data Index: 126332 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.2114. Min Act: -0.0001

Data Index: 789283 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.9514. Min Act: -0.0001

Data Index: 413577 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.6720. Min Act: -0.0001

Data Index: 748322 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.9312. Min Act: -0.0001

Data Index: 74680 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.3428. Min Act: -0.0001

Data Index: 1299148 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.5883. Min Act: -0.0001

Data Index: 1113286 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.7220. Min Act: -0.0001

Data Index: 477459 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.8348. Min Act: -0.0001

Data Index: 1086688 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.4292. Min Act: -0.0001

Data Index: 1145404 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.8446. Min Act: -0.0001

Data Index: 484685 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.9124. Min Act: -0.0001

Data Index: 687294 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.6391. Min Range: -3.6391

Max Act: 2.9075. Min Act: -0.0001

Data Index: 214901 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.6391. Min Range: -3.6391

Max Act: 3.1358. Min Act: -0.0001

Data Index: 182245 (C4 (Web Text))

Max Activating Token Index: 658