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

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

Neuron 4247 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: 2.8555. Min Range: -2.8555

Max Act: 2.8555. Min Act: -0.0000

Data Index: 1278768 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.3811. Min Act: -0.0000

Data Index: 724478 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1074407 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.2053. Min Act: -0.0000

Data Index: 280346 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.1686. Min Act: -0.0000

Data Index: 1150840 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.1625. Min Act: -0.0000

Data Index: 1251721 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.0910. Min Act: -0.0000

Data Index: 383461 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.0499. Min Act: -0.0000

Data Index: 504652 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.1588. Min Act: -0.0000

Data Index: 505176 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 2.8555. Min Range: -2.8555

Max Act: 2.0279. Min Act: -0.0000

Data Index: 200063 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9395. Min Act: -0.0000

Data Index: 33772 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9471. Min Act: -0.0000

Data Index: 173214 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9175. Min Act: 0.0000

Data Index: 14550 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9089. Min Act: -0.0000

Data Index: 1096980 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.8797. Min Act: -0.0000

Data Index: 323111 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9709. Min Act: -0.0000

Data Index: 220261 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.8800. Min Act: -0.0000

Data Index: 310179 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.7346. Min Act: -0.0000

Data Index: 353891 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9560. Min Act: -0.0000

Data Index: 375317 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 2.8555. Min Range: -2.8555

Max Act: 1.9177. Min Act: -0.0000

Data Index: 740378 (C4 (Web Text))

Max Activating Token Index: 377