Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2363 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3885. Min Act: -0.0000

Data Index: 787237 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3553. Min Act: -0.0000

Data Index: 151818 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1209580 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3317. Min Act: -0.0000

Data Index: 632791 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1282484 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3076. Min Act: -0.0000

Data Index: 726897 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3231. Min Act: -0.0000

Data Index: 639101 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3012. Min Act: -0.0000

Data Index: 642308 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2965. Min Act: -0.0000

Data Index: 856359 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2960. Min Act: -0.0000

Data Index: 799091 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1351652 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2918. Min Act: -0.0000

Data Index: 455376 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2795. Min Act: -0.0000

Data Index: 97865 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1013922 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1296803 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2886. Min Act: -0.0000

Data Index: 221895 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2848. Min Act: -0.0000

Data Index: 947696 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2736. Min Act: -0.0000

Data Index: 15071 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2713. Min Act: -0.0000

Data Index: 177069 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.2708. Min Act: -0.0000

Data Index: 566427 (C4 (Web Text))

Max Activating Token Index: 609