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

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

Neuron 1913 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1224. Min Act: -0.0000

Data Index: 613021 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.1654. Min Act: -0.0000

Data Index: 821388 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.1654. Min Range: -1.1654

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1640825 (Python Code)

Max Activating Token Index: 241

Text #3

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9706. Min Act: -0.0000

Data Index: 348247 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.9038. Min Act: -0.0000

Data Index: 871474 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8150. Min Act: -0.0000

Data Index: 864974 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8401. Min Act: -0.0000

Data Index: 397212 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8055. Min Act: -0.0000

Data Index: 711201 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8719. Min Act: -0.0000

Data Index: 872880 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1185133 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1048322 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.8144. Min Act: -0.0000

Data Index: 967103 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.7626. Min Act: -0.0000

Data Index: 394530 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.7320. Min Act: -0.0000

Data Index: 972414 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.7303. Min Act: -0.0000

Data Index: 115204 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.7115. Min Act: -0.0000

Data Index: 293586 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1050144 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1587757 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.6898. Min Act: -0.0000

Data Index: 621011 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 1.1654. Min Range: -1.1654

Max Act: 0.6688. Min Act: -0.0000

Data Index: 902149 (C4 (Web Text))

Max Activating Token Index: 824