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

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

Neuron 2790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.7574. Min Act: -0.0000

Data Index: 428708 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.3641. Min Act: -0.0000

Data Index: 251935 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.5727. Min Act: -0.0000

Data Index: 718737 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.4922. Min Act: -0.0000

Data Index: 1159 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.6414. Min Act: -0.0000

Data Index: 1068448 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.6196. Min Act: -0.0000

Data Index: 852124 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1314294 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.3127. Min Act: -0.0000

Data Index: 942186 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.4485. Min Act: -0.0000

Data Index: 331465 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.1567. Min Act: -0.0000

Data Index: 433954 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.1728. Min Act: -0.0000

Data Index: 341435 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1052423 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.0184. Min Act: -0.0000

Data Index: 997134 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 2.7574. Min Range: -2.7574

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1102956 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.3078. Min Act: -0.0000

Data Index: 1187470 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.2627. Min Act: -0.0000

Data Index: 645417 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 2.7574. Min Range: -2.7574

Max Act: 1.9187. Min Act: -0.0000

Data Index: 952417 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 2.7574. Min Range: -2.7574

Max Act: 1.9160. Min Act: -0.0000

Data Index: 1256641 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 2.7574. Min Range: -2.7574

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1122404 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 2.7574. Min Range: -2.7574

Max Act: 1.8824. Min Act: -0.0000

Data Index: 324771 (C4 (Web Text))

Max Activating Token Index: 774