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

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

Neuron 2925 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0150. Min Range: -1.0150

Max Act: 1.0150. Min Act: -0.0000

Data Index: 526560 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6443. Min Act: -0.0000

Data Index: 377132 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6727. Min Act: -0.0001

Data Index: 660348 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6221. Min Act: -0.0000

Data Index: 935041 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6535. Min Act: -0.0000

Data Index: 293006 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1157783 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1115121 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5916. Min Act: -0.0001

Data Index: 399474 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6398. Min Act: -0.0001

Data Index: 849685 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5441. Min Act: -0.0000

Data Index: 64328 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1244903 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1060234 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5398. Min Act: -0.0000

Data Index: 670730 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1122391 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1258143 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5772. Min Act: -0.0000

Data Index: 474782 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1142666 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1261004 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5164. Min Act: -0.0001

Data Index: 624332 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.0150. Min Range: -1.0150

Max Act: 0.5396. Min Act: -0.0000

Data Index: 893773 (C4 (Web Text))

Max Activating Token Index: 739