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

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

Neuron 161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1146200 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3562. Min Act: -0.0001

Data Index: 1466433 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3426. Min Act: -0.0001

Data Index: 662742 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3363. Min Act: -0.0000

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1259608 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3284. Min Act: -0.0000

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3147. Min Act: -0.0000

Data Index: 54049 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3142. Min Act: -0.0000

Data Index: 156534 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3076. Min Act: -0.0001

Data Index: 902952 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1545295 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2815. Min Act: -0.0001

Data Index: 1449335 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2787. Min Act: -0.0001

Data Index: 360575 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1527488 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2949. Min Act: -0.0000

Data Index: 7720 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2768. Min Act: -0.0001

Data Index: 1526486 (Python Code)

Max Activating Token Index: 392

Text #15

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2855. Min Act: -0.0001

Data Index: 167607 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2837. Min Act: -0.0001

Data Index: 81826 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1574552 (Python Code)

Max Activating Token Index: 889

Text #18

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2905. Min Act: -0.0001

Data Index: 623213 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.3562. Min Range: -0.3562

Max Act: 0.2753. Min Act: -0.0001

Data Index: 1374183 (Python Code)

Max Activating Token Index: 854