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

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

Neuron 4006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1114979 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1652002 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8544. Min Act: -0.0000

Data Index: 386296 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1494018 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.9147. Min Act: -0.0000

Data Index: 852377 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1013795 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8673. Min Act: -0.0000

Data Index: 95000 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8432. Min Act: -0.0000

Data Index: 471545 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7344. Min Act: -0.0000

Data Index: 868446 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7201. Min Act: -0.0000

Data Index: 358281 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8089. Min Act: -0.0000

Data Index: 288251 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8281. Min Act: -0.0000

Data Index: 939334 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1461654 (Python Code)

Max Activating Token Index: 340

Text #13

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7706. Min Act: -0.0000

Data Index: 776763 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7747. Min Act: -0.0000

Data Index: 127123 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1643237 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7206. Min Act: -0.0000

Data Index: 967006 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1475081 (Python Code)

Max Activating Token Index: 271

Text #18

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7374. Min Act: -0.0000

Data Index: 77090 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.9810. Min Range: -0.9810

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1591171 (Python Code)

Max Activating Token Index: 38