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

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

Neuron 2858 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1461765 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1475459 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1639127 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1588210 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1452234 (Python Code)

Max Activating Token Index: 550

Text #5

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1547667 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1374378 (Python Code)

Max Activating Token Index: 258

Text #7

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1642687 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1561139 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1367360 (Python Code)

Max Activating Token Index: 493

Text #10

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1444576 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1461319 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1441226 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1373798 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1614709 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1481179 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1549797 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1452920 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.6763. Min Act: -0.0000

Data Index: 1550247 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 0.8781. Min Range: -0.8781

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1547046 (Python Code)

Max Activating Token Index: 26