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

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

Neuron 166 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.6101. Min Act: -0.0000

Data Index: 122008 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.7306. Min Act: -0.0000

Data Index: 945914 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.5976. Min Act: -0.0000

Data Index: 1372819 (Python Code)

Max Activating Token Index: 410

Text #3

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.2192. Min Act: -0.0000

Data Index: 1530318 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.4571. Min Act: -0.0000

Data Index: 1644343 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.3924. Min Act: -0.0000

Data Index: 1604647 (Python Code)

Max Activating Token Index: 500

Text #6

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.0688. Min Act: -0.0000

Data Index: 1609606 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.5373. Min Act: -0.0000

Data Index: 1398837 (Python Code)

Max Activating Token Index: 278

Text #8

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.1775. Min Act: -0.0000

Data Index: 941273 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.3157. Min Act: -0.0000

Data Index: 1511799 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.4374. Min Act: -0.0000

Data Index: 1609569 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.2253. Min Act: -0.0000

Data Index: 1528679 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.0742. Min Act: -0.0000

Data Index: 1360319 (Python Code)

Max Activating Token Index: 559

Text #13

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.0694. Min Act: -0.0000

Data Index: 1410780 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.2082. Min Act: -0.0000

Data Index: 1462130 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.1065. Min Act: -0.0000

Data Index: 1415601 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.0404. Min Act: -0.0000

Data Index: 1515606 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 5.6101. Min Range: -5.6101

Max Act: 3.8890. Min Act: -0.0000

Data Index: 1532279 (Python Code)

Max Activating Token Index: 489

Text #18

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.0612. Min Act: -0.0000

Data Index: 1612631 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 5.6101. Min Range: -5.6101

Max Act: 4.2508. Min Act: -0.0000

Data Index: 1588341 (Python Code)

Max Activating Token Index: 837