Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.2757. Min Act: -0.0002

Data Index: 679925 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.1905. Min Act: -0.0002

Data Index: 974784 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.1568. Min Act: -0.0002

Data Index: 567969 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9868. Min Act: -0.0002

Data Index: 99929 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.2757. Min Range: -1.2757

Max Act: 1.0628. Min Act: -0.0002

Data Index: 722150 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9934. Min Act: -0.0002

Data Index: 631354 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9287. Min Act: -0.0002

Data Index: 597761 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9708. Min Act: -0.0002

Data Index: 1017063 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9620. Min Act: -0.0002

Data Index: 161957 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9279. Min Act: -0.0002

Data Index: 878496 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8586. Min Act: -0.0002

Data Index: 586631 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8791. Min Act: -0.0002

Data Index: 1327469 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9350. Min Act: -0.0002

Data Index: 70118 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.9002. Min Act: -0.0002

Data Index: 109019 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8361. Min Act: -0.0002

Data Index: 455405 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8524. Min Act: -0.0002

Data Index: 1938 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8736. Min Act: -0.0002

Data Index: 1030157 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8369. Min Act: -0.0002

Data Index: 533572 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8396. Min Act: -0.0002

Data Index: 1338354 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.2757. Min Range: -1.2757

Max Act: 0.8376. Min Act: -0.0002

Data Index: 994330 (C4 (Web Text))

Max Activating Token Index: 192