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

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

Neuron 2478 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2796. Min Range: -7.2796

Max Act: 7.2796. Min Act: -0.0000

Data Index: 833816 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 7.2796. Min Range: -7.2796

Max Act: 6.5737. Min Act: -0.0000

Data Index: 90312 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 7.2796. Min Range: -7.2796

Max Act: 6.3612. Min Act: -0.0000

Data Index: 1044862 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 7.2796. Min Range: -7.2796

Max Act: 6.3256. Min Act: -0.0000

Data Index: 614780 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.9592. Min Act: -0.0000

Data Index: 489066 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.4889. Min Act: -0.0000

Data Index: 1122759 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.5845. Min Act: -0.0000

Data Index: 770835 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.3930. Min Act: -0.0000

Data Index: 227088 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.2459. Min Act: -0.0000

Data Index: 1066390 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.9760. Min Act: -0.0000

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.1019. Min Act: -0.0000

Data Index: 16367 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.2705. Min Act: -0.0000

Data Index: 1068498 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.8595. Min Act: -0.0000

Data Index: 595121 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.0394. Min Act: -0.0000

Data Index: 61947 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.9406. Min Act: -0.0000

Data Index: 171902 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 7.2796. Min Range: -7.2796

Max Act: 5.1580. Min Act: -0.0000

Data Index: 483337 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.7326. Min Act: -0.0000

Data Index: 256568 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.7823. Min Act: -0.0000

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.9337. Min Act: -0.0000

Data Index: 576955 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 7.2796. Min Range: -7.2796

Max Act: 4.7138. Min Act: -0.0000

Data Index: 133845 (C4 (Web Text))

Max Activating Token Index: 953