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

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

Neuron 4461 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3871. Min Act: -0.0002

Data Index: 1166745 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: -0.0002

Data Index: 1154977 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2935. Min Act: -0.0002

Data Index: 952981 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2373. Min Act: -0.0002

Data Index: 1187070 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2360. Min Act: -0.0002

Data Index: 1021483 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2285. Min Act: -0.0002

Data Index: 13204 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2332. Min Act: -0.0002

Data Index: 24510 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2211. Min Act: -0.0002

Data Index: 855929 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2227. Min Act: -0.0002

Data Index: 157208 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2589. Min Act: -0.0002

Data Index: 15876 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1699. Min Act: -0.0002

Data Index: 172457 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1744. Min Act: -0.0002

Data Index: 744330 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1859. Min Act: -0.0002

Data Index: 1210136 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1887. Min Act: -0.0002

Data Index: 945498 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1770. Min Act: -0.0002

Data Index: 59902 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1641. Min Act: -0.0002

Data Index: 690604 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1518. Min Act: -0.0002

Data Index: 1247977 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1670. Min Act: -0.0002

Data Index: 1301100 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1434. Min Act: -0.0002

Data Index: 248002 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1515. Min Act: -0.0002

Data Index: 262358 (C4 (Web Text))

Max Activating Token Index: 263