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

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

Neuron 2703 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: 0.8374. Min Range: -0.8374

Max Act: 0.8374. Min Act: -0.0000

Data Index: 933898 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.7885. Min Act: -0.0000

Data Index: 463362 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6945. Min Act: -0.0000

Data Index: 217724 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1141333 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1091081 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6682. Min Act: -0.0000

Data Index: 363930 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6856. Min Act: -0.0000

Data Index: 285811 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1028572 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6568. Min Act: -0.0000

Data Index: 730634 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6269. Min Act: -0.0000

Data Index: 797057 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6400. Min Act: -0.0000

Data Index: 431711 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6023. Min Act: -0.0000

Data Index: 329754 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6233. Min Act: -0.0000

Data Index: 711851 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5761. Min Act: -0.0000

Data Index: 733273 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6328. Min Act: -0.0000

Data Index: 850517 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6125. Min Act: -0.0000

Data Index: 938008 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.6040. Min Act: -0.0000

Data Index: 690781 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5865. Min Act: -0.0000

Data Index: 900712 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5971. Min Act: -0.0000

Data Index: 87247 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.8374. Min Range: -0.8374

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1324851 (C4 (Web Text))

Max Activating Token Index: 59