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

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

Neuron 3222 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1300. Min Range: -2.1300

Max Act: 2.1300. Min Act: -0.0000

Data Index: 699103 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.8511. Min Act: -0.0000

Data Index: 844131 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.7108. Min Act: -0.0000

Data Index: 268417 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.6934. Min Act: -0.0000

Data Index: 353956 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1014659 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.7045. Min Act: -0.0000

Data Index: 135619 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.6061. Min Act: -0.0000

Data Index: 741998 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.5789. Min Act: -0.0000

Data Index: 801346 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1179631 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.5371. Min Act: -0.0000

Data Index: 1231630 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1061247 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4621. Min Act: -0.0000

Data Index: 858173 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1003954 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4361. Min Act: -0.0000

Data Index: 143696 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4216. Min Act: -0.0000

Data Index: 100874 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4148. Min Act: -0.0000

Data Index: 331954 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.4085. Min Act: -0.0000

Data Index: 731987 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.2946. Min Act: 0.0000

Data Index: 830518 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.3735. Min Act: 0.0000

Data Index: 1352817 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 2.1300. Min Range: -2.1300

Max Act: 1.3687. Min Act: -0.0000

Data Index: 795318 (C4 (Web Text))

Max Activating Token Index: 717