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

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

Neuron 3665 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: 9.3114. Min Range: -9.3114

Max Act: 9.3114. Min Act: -0.0000

Data Index: 1654248 (Python Code)

Max Activating Token Index: 469

Text #1

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.7315. Min Act: -0.0000

Data Index: 1629706 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.6800. Min Act: -0.0000

Data Index: 1643579 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.4211. Min Act: -0.0000

Data Index: 1384805 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.2646. Min Act: -0.0000

Data Index: 1405681 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.9918. Min Act: -0.0000

Data Index: 1459041 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.0397. Min Act: -0.0000

Data Index: 1471459 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.8500. Min Act: -0.0000

Data Index: 1504888 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 9.3114. Min Range: -9.3114

Max Act: 8.0556. Min Act: -0.0000

Data Index: 1404572 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.8387. Min Act: -0.0000

Data Index: 1467162 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.5717. Min Act: -0.0000

Data Index: 1563250 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.7204. Min Act: -0.0000

Data Index: 1428022 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.5316. Min Act: -0.0000

Data Index: 1561891 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.5110. Min Act: -0.0000

Data Index: 1627885 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.3056. Min Act: -0.0000

Data Index: 1385126 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.4758. Min Act: -0.0000

Data Index: 1364468 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.6332. Min Act: -0.0000

Data Index: 1381576 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.4516. Min Act: -0.0000

Data Index: 1400623 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.4157. Min Act: -0.0000

Data Index: 1502983 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 9.3114. Min Range: -9.3114

Max Act: 7.5775. Min Act: -0.0000

Data Index: 1647271 (Python Code)

Max Activating Token Index: 1015