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

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

Neuron 1294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9655. Min Range: -4.9655

Max Act: 4.9655. Min Act: -0.0000

Data Index: 573549 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 4.9655. Min Range: -4.9655

Max Act: 4.1539. Min Act: -0.0000

Data Index: 717437 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 4.9655. Min Range: -4.9655

Max Act: 4.1426. Min Act: -0.0000

Data Index: 1579353 (Python Code)

Max Activating Token Index: 693

Text #3

Max Range: 4.9655. Min Range: -4.9655

Max Act: 4.2051. Min Act: -0.0000

Data Index: 129383 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 4.9655. Min Range: -4.9655

Max Act: 4.0679. Min Act: -0.0000

Data Index: 330820 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.7248. Min Act: -0.0000

Data Index: 47323 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.8744. Min Act: -0.0000

Data Index: 993966 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.6671. Min Act: -0.0000

Data Index: 606540 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.8087. Min Act: -0.0000

Data Index: 497764 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.5323. Min Act: -0.0000

Data Index: 927875 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.4003. Min Act: -0.0000

Data Index: 472562 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.5957. Min Act: -0.0000

Data Index: 717322 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.5984. Min Act: -0.0000

Data Index: 456501 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.4027. Min Act: -0.0000

Data Index: 10518 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 4.9655. Min Range: -4.9655

Max Act: 2.7596. Min Act: -0.0000

Data Index: 690082 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.5689. Min Act: -0.0000

Data Index: 11443 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.3653. Min Act: -0.0000

Data Index: 994590 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.2710. Min Act: -0.0000

Data Index: 1155296 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.2570. Min Act: -0.0000

Data Index: 1123155 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 4.9655. Min Range: -4.9655

Max Act: 3.1096. Min Act: -0.0000

Data Index: 67360 (C4 (Web Text))

Max Activating Token Index: 143