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

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

Neuron 1944 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: 2.3546. Min Range: -2.3546

Max Act: 1.9487. Min Act: -0.0000

Data Index: 97507 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 2.3546. Min Range: -2.3546

Max Act: 2.0455. Min Act: -0.0000

Data Index: 1655665 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 2.3546. Min Range: -2.3546

Max Act: 2.3546. Min Act: -0.0000

Data Index: 1368567 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 2.3546. Min Range: -2.3546

Max Act: 2.0391. Min Act: -0.0000

Data Index: 1435197 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 2.3546. Min Range: -2.3546

Max Act: 2.0029. Min Act: -0.0000

Data Index: 1013034 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8045. Min Act: -0.0000

Data Index: 467427 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1585771 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9428. Min Act: -0.0000

Data Index: 1537791 (Python Code)

Max Activating Token Index: 541

Text #8

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9398. Min Act: -0.0000

Data Index: 189146 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8245. Min Act: -0.0000

Data Index: 338329 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9939. Min Act: -0.0000

Data Index: 1492541 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8625. Min Act: -0.0000

Data Index: 1490258 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9237. Min Act: -0.0000

Data Index: 682105 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8635. Min Act: -0.0000

Data Index: 1133115 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8220. Min Act: -0.0000

Data Index: 727733 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9322. Min Act: -0.0000

Data Index: 1074058 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.7203. Min Act: -0.0000

Data Index: 361133 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 2.3546. Min Range: -2.3546

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1415902 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 2.3546. Min Range: -2.3546

Max Act: 1.9527. Min Act: -0.0000

Data Index: 1291699 (C4 (Web Text))

Max Activating Token Index: 877