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

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

Neuron 3087 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4186. Min Range: -1.4186

Max Act: 1.4186. Min Act: -0.0000

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.4186. Min Range: -1.4186

Max Act: 1.1551. Min Act: -0.0000

Data Index: 778373 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.9762. Min Act: -0.0000

Data Index: 153626 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.4186. Min Range: -1.4186

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1599560 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 1.4186. Min Range: -1.4186

Max Act: 1.0082. Min Act: -0.0000

Data Index: 172721 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8781. Min Act: -0.0000

Data Index: 324597 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.4186. Min Range: -1.4186

Max Act: 1.0629. Min Act: -0.0000

Data Index: 678109 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.9399. Min Act: -0.0000

Data Index: 339043 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8784. Min Act: -0.0000

Data Index: 711297 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.9752. Min Act: -0.0000

Data Index: 948471 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1634523 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.9193. Min Act: -0.0000

Data Index: 885439 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.9264. Min Act: -0.0000

Data Index: 859096 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1442543 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1653057 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8678. Min Act: -0.0000

Data Index: 966509 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1430583 (Python Code)

Max Activating Token Index: 150

Text #17

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1512532 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1062434 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.4186. Min Range: -1.4186

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1409562 (Python Code)

Max Activating Token Index: 190