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

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

Neuron 654 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: 0.4897. Min Range: -0.4897

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1004694 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4697. Min Act: -0.0000

Data Index: 801551 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4720. Min Act: -0.0000

Data Index: 261537 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4390. Min Act: -0.0000

Data Index: 274517 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1171293 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1030133 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4602. Min Act: -0.0000

Data Index: 228096 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4430. Min Act: -0.0000

Data Index: 268914 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4897. Min Act: -0.0000

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4516. Min Act: -0.0000

Data Index: 124950 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4396. Min Act: -0.0000

Data Index: 974330 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4346. Min Act: -0.0000

Data Index: 681946 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1077017 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4296. Min Act: -0.0000

Data Index: 768076 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4379. Min Act: -0.0000

Data Index: 2270 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4317. Min Act: -0.0000

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4307. Min Act: -0.0000

Data Index: 808655 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1206803 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4554. Min Act: -0.0000

Data Index: 849132 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4617. Min Act: -0.0000

Data Index: 446273 (C4 (Web Text))

Max Activating Token Index: 975