Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 353 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.9666. Min Act: -0.0000

Data Index: 718258 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.7479. Min Act: -0.0001

Data Index: 503849 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.5705. Min Act: -0.0000

Data Index: 222770 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.3882. Min Act: -0.0001

Data Index: 54242 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2654. Min Act: -0.0001

Data Index: 1342993 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.3362. Min Act: -0.0001

Data Index: 1232305 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.3360. Min Act: -0.0001

Data Index: 387610 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2850. Min Act: -0.0001

Data Index: 402835 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.3264. Min Act: -0.0001

Data Index: 68232 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2846. Min Act: -0.0001

Data Index: 888045 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2854. Min Act: -0.0001

Data Index: 11333 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1034563 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2484. Min Act: -0.0001

Data Index: 394203 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2876. Min Act: -0.0000

Data Index: 452029 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2125. Min Act: -0.0000

Data Index: 330241 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2220. Min Act: -0.0001

Data Index: 688043 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.1948. Min Act: -0.0001

Data Index: 158648 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.1816. Min Act: -0.0001

Data Index: 810663 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.2147. Min Act: -0.0001

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 1.9666. Min Range: -1.9666

Max Act: 1.1821. Min Act: -0.0001

Data Index: 586885 (C4 (Web Text))

Max Activating Token Index: 408