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

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

Neuron 1500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1032976 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1544. Min Act: -0.0000

Data Index: 256311 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1468. Min Act: -0.0000

Data Index: 758014 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1498582 (Python Code)

Max Activating Token Index: 206

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1362. Min Act: -0.0000

Data Index: 193526 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1280. Min Act: -0.0000

Data Index: 128837 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1094564 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1231. Min Act: -0.0000

Data Index: 127338 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1222. Min Act: -0.0000

Data Index: 73185 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1278. Min Act: -0.0000

Data Index: 15160 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1298. Min Act: -0.0000

Data Index: 825567 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1192. Min Act: -0.0000

Data Index: 933615 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1291. Min Act: -0.0000

Data Index: 551043 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1229. Min Act: -0.0000

Data Index: 626665 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1281. Min Act: -0.0000

Data Index: 702319 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1279355 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1287009 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1277. Min Act: -0.0000

Data Index: 579663 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1272. Min Act: -0.0000

Data Index: 994992 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1203481 (C4 (Web Text))

Max Activating Token Index: 684