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

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

Neuron 4547 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.3971. Min Act: -0.0000

Data Index: 188015 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.1570. Min Act: -0.0000

Data Index: 7402 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.2509. Min Act: -0.0000

Data Index: 944847 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1080411 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.1025. Min Act: -0.0000

Data Index: 841687 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1195424 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.0374. Min Act: -0.0000

Data Index: 844718 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.0051. Min Act: -0.0000

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9617. Min Act: -0.0000

Data Index: 876361 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 1.3971. Min Range: -1.3971

Max Act: 1.0437. Min Act: -0.0000

Data Index: 21792 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9829. Min Act: -0.0000

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9766. Min Act: -0.0000

Data Index: 942652 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1336741 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.8795. Min Act: -0.0000

Data Index: 241797 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9383. Min Act: -0.0000

Data Index: 556348 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.8779. Min Act: -0.0000

Data Index: 579537 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9070. Min Act: -0.0000

Data Index: 713222 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9065. Min Act: -0.0000

Data Index: 156655 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.8881. Min Act: -0.0000

Data Index: 480774 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.3971. Min Range: -1.3971

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1331581 (C4 (Web Text))

Max Activating Token Index: 940