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

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

Neuron 4093 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1925. Min Act: -0.0001

Data Index: 1255602 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.1925. Min Range: -1.1925

Max Act: 1.1531. Min Act: -0.0001

Data Index: 1240009 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9056. Min Act: -0.0001

Data Index: 167267 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8620. Min Act: -0.0001

Data Index: 96237 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9326. Min Act: -0.0001

Data Index: 907832 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8423. Min Act: -0.0001

Data Index: 83551 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8753. Min Act: -0.0001

Data Index: 252212 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1210947 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8546. Min Act: -0.0001

Data Index: 1325592 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.9000. Min Act: -0.0001

Data Index: 172085 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8566. Min Act: -0.0001

Data Index: 1025074 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8320. Min Act: -0.0001

Data Index: 659848 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1146150 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1014547 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8225. Min Act: -0.0001

Data Index: 19276 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1058216 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.7403. Min Act: -0.0001

Data Index: 1053474 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.7983. Min Act: -0.0001

Data Index: 874653 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.8467. Min Act: -0.0001

Data Index: 1291150 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.1925. Min Range: -1.1925

Max Act: 0.7789. Min Act: -0.0001

Data Index: 545989 (C4 (Web Text))

Max Activating Token Index: 441