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

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

Neuron 2995 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.3446. Min Act: -0.0000

Data Index: 729782 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2919. Min Act: -0.0000

Data Index: 656297 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2256. Min Act: -0.0000

Data Index: 678227 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1095517 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1067054 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1989. Min Act: -0.0000

Data Index: 940296 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2065. Min Act: -0.0000

Data Index: 560519 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2069. Min Act: -0.0000

Data Index: 346696 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1872. Min Act: -0.0000

Data Index: 740161 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1923. Min Act: -0.0000

Data Index: 228029 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1857. Min Act: -0.0000

Data Index: 786537 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1919. Min Act: -0.0000

Data Index: 400557 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1788. Min Act: -0.0000

Data Index: 185356 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1278436 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1105943 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1818. Min Act: -0.0000

Data Index: 271383 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1910. Min Act: -0.0000

Data Index: 530919 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1867. Min Act: -0.0000

Data Index: 925381 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1721. Min Act: -0.0000

Data Index: 871663 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1780. Min Act: -0.0000

Data Index: 552107 (C4 (Web Text))

Max Activating Token Index: 225