Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 57 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3762. Min Range: -2.3762

Max Act: 2.3762. Min Act: -0.0000

Data Index: 205995 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 2.3762. Min Range: -2.3762

Max Act: 2.1842. Min Act: -0.0000

Data Index: 1077501 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 2.3762. Min Range: -2.3762

Max Act: 2.0389. Min Act: -0.0000

Data Index: 507081 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 2.3762. Min Range: -2.3762

Max Act: 2.0134. Min Act: -0.0000

Data Index: 602741 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.9584. Min Act: 0.0000

Data Index: 1297570 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.9399. Min Act: -0.0000

Data Index: 84021 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1342655 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.8206. Min Act: -0.0000

Data Index: 87480 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1051072 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.8221. Min Act: -0.0000

Data Index: 161319 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7735. Min Act: -0.0000

Data Index: 1215753 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1214234 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.6563. Min Act: -0.0000

Data Index: 662175 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1308600 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7385. Min Act: -0.0000

Data Index: 342046 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7371. Min Act: -0.0000

Data Index: 94445 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7281. Min Act: -0.0000

Data Index: 987601 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.6250. Min Act: -0.0000

Data Index: 1072844 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.7039. Min Act: -0.0000

Data Index: 1028448 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 2.3762. Min Range: -2.3762

Max Act: 1.6925. Min Act: -0.0000

Data Index: 602628 (C4 (Web Text))

Max Activating Token Index: 30