Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 323 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0540. Min Act: -0.0003

Data Index: 861004 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1350500 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1082617 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0471. Min Act: -0.0003

Data Index: 475068 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0423. Min Act: -0.0003

Data Index: 343730 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0485. Min Act: -0.0003

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1050800 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0468. Min Act: -0.0003

Data Index: 666760 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1120120 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0427. Min Act: -0.0003

Data Index: 736615 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1001923 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0442. Min Act: -0.0003

Data Index: 67335 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0449. Min Act: -0.0003

Data Index: 764603 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0442. Min Act: -0.0003

Data Index: 740577 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1043033 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0439. Min Act: -0.0003

Data Index: 140023 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1321549 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1191073 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0405. Min Act: -0.0003

Data Index: 62293 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.0540. Min Range: -0.0540

Max Act: 0.0415. Min Act: -0.0003

Data Index: 967431 (C4 (Web Text))

Max Activating Token Index: 849