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

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

Neuron 5856 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: 1.0690. Min Range: -1.0690

Max Act: 1.0690. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.9565. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.9334. Min Act: -0.0000

Data Index: 113943 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.8239. Min Act: -0.0000

Data Index: 1172029 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1120936 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6926. Min Act: -0.0000

Data Index: 526748 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1587701 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1379439 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6174. Min Act: -0.0000

Data Index: 541873 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5218. Min Act: -0.0000

Data Index: 285384 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1429476 (Python Code)

Max Activating Token Index: 196

Text #11

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5246. Min Act: -0.0000

Data Index: 816358 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.6267. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1197121 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5038. Min Act: -0.0000

Data Index: 270121 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1119174 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5988. Min Act: -0.0000

Data Index: 961939 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5751. Min Act: -0.0000

Data Index: 904990 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1501546 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 1.0690. Min Range: -1.0690

Max Act: 0.5553. Min Act: -0.0000

Data Index: 227413 (C4 (Web Text))

Max Activating Token Index: 687