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

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

Neuron 674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2274. Min Act: -0.0000

Data Index: 615794 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0000

Data Index: 756457 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2146. Min Act: -0.0000

Data Index: 151458 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1958. Min Act: -0.0000

Data Index: 120102 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1330944 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2077. Min Act: -0.0001

Data Index: 280164 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1990. Min Act: -0.0000

Data Index: 837239 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1153461 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1855. Min Act: -0.0000

Data Index: 707196 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2170. Min Act: -0.0001

Data Index: 865013 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1193591 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1912. Min Act: -0.0000

Data Index: 400431 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1919. Min Act: -0.0001

Data Index: 145066 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1901. Min Act: -0.0000

Data Index: 632073 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1817. Min Act: -0.0000

Data Index: 873267 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1139042 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1307053 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1769. Min Act: -0.0000

Data Index: 358707 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1017715 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1787. Min Act: -0.0000

Data Index: 386942 (C4 (Web Text))

Max Activating Token Index: 985