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

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

Neuron 623 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.8769. Min Act: -0.0000

Data Index: 961921 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.5521. Min Act: -0.0000

Data Index: 1362274 (Python Code)

Max Activating Token Index: 627

Text #2

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.4274. Min Act: -0.0000

Data Index: 1523957 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.2774. Min Act: -0.0000

Data Index: 444983 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.1491. Min Act: -0.0000

Data Index: 858386 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.2091. Min Act: -0.0000

Data Index: 64475 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0526. Min Act: -0.0000

Data Index: 698269 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1472601 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1429929 (Python Code)

Max Activating Token Index: 959

Text #9

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1284701 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0092. Min Act: -0.0000

Data Index: 494486 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0013. Min Act: -0.0000

Data Index: 400 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1408488 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.0387. Min Act: -0.0000

Data Index: 1568065 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.9446. Min Act: -0.0000

Data Index: 204543 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.8881. Min Act: -0.0000

Data Index: 82023 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.8681. Min Act: -0.0000

Data Index: 422720 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1469877 (Python Code)

Max Activating Token Index: 421

Text #18

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.8418. Min Act: -0.0000

Data Index: 446098 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.8769. Min Range: -1.8769

Max Act: 0.8145. Min Act: -0.0000

Data Index: 472699 (C4 (Web Text))

Max Activating Token Index: 457