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

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

Neuron 4499 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: 0.9414. Min Range: -0.9414

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1137012 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9414. Min Act: -0.0000

Data Index: 467083 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1003439 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8383. Min Act: -0.0000

Data Index: 801831 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8594. Min Act: -0.0000

Data Index: 933633 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1057365 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7990. Min Act: -0.0000

Data Index: 711144 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1182998 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7558. Min Act: -0.0000

Data Index: 31523 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1303192 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7919. Min Act: -0.0000

Data Index: 661799 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7435. Min Act: 0.0000

Data Index: 1036938 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7736. Min Act: -0.0000

Data Index: 368278 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7709. Min Act: -0.0000

Data Index: 554448 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1068455 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7266. Min Act: -0.0000

Data Index: 834814 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6863. Min Act: -0.0000

Data Index: 238269 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1204700 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1243001 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1207376 (C4 (Web Text))

Max Activating Token Index: 541