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

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

Neuron 1399 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.3330. Min Act: -0.0000

Data Index: 362110 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.3162. Min Act: -0.0000

Data Index: 998211 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1425284 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.2564. Min Act: -0.0000

Data Index: 233207 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1591. Min Act: -0.0000

Data Index: 893610 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1215. Min Act: -0.0000

Data Index: 650757 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1571656 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1499477 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1384. Min Act: -0.0000

Data Index: 235933 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1798. Min Act: -0.0000

Data Index: 1538276 (Python Code)

Max Activating Token Index: 684

Text #10

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1754. Min Act: -0.0000

Data Index: 905389 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1461570 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1392621 (Python Code)

Max Activating Token Index: 219

Text #13

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1589131 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1892. Min Act: -0.0000

Data Index: 224196 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1027479 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1721. Min Act: -0.0000

Data Index: 930598 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.0994. Min Act: -0.0000

Data Index: 356172 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.0981. Min Act: -0.0000

Data Index: 76769 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.3330. Min Range: -1.3330

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1515391 (Python Code)

Max Activating Token Index: 799