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

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

Neuron 4160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.1355. Min Act: -0.0000

Data Index: 457782 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0955. Min Act: -0.0000

Data Index: 785836 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0381. Min Act: -0.0000

Data Index: 360033 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0260. Min Act: 0.0000

Data Index: 1003760 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0089. Min Act: -0.0000

Data Index: 957419 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0260. Min Act: -0.0000

Data Index: 255570 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9956. Min Act: -0.0000

Data Index: 819075 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1131109 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0253. Min Act: -0.0000

Data Index: 644247 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1120105 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9004. Min Act: -0.0000

Data Index: 489719 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9229. Min Act: -0.0000

Data Index: 304377 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 1.1355. Min Range: -1.1355

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1217666 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9403. Min Act: -0.0000

Data Index: 979905 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9379. Min Act: -0.0000

Data Index: 814436 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9346. Min Act: -0.0000

Data Index: 291362 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.8969. Min Act: -0.0000

Data Index: 859038 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9551. Min Act: -0.0000

Data Index: 500118 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9109. Min Act: -0.0000

Data Index: 290447 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.1355. Min Range: -1.1355

Max Act: 0.9150. Min Act: -0.0000

Data Index: 458780 (C4 (Web Text))

Max Activating Token Index: 148