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

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

Neuron 4346 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: 2.3257. Min Range: -2.3257

Max Act: 2.3257. Min Act: -0.0000

Data Index: 1287599 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 2.3257. Min Range: -2.3257

Max Act: 2.1309. Min Act: -0.0000

Data Index: 796297 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 2.3257. Min Range: -2.3257

Max Act: 2.1065. Min Act: -0.0000

Data Index: 1197218 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 2.3257. Min Range: -2.3257

Max Act: 2.0781. Min Act: -0.0000

Data Index: 880582 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 2.3257. Min Range: -2.3257

Max Act: 2.0557. Min Act: -0.0000

Data Index: 119605 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.3257. Min Range: -2.3257

Max Act: 2.0097. Min Act: -0.0000

Data Index: 917197 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8537. Min Act: -0.0000

Data Index: 1471890 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8355. Min Act: -0.0000

Data Index: 1238517 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.9233. Min Act: -0.0000

Data Index: 414789 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8435. Min Act: -0.0000

Data Index: 703543 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8471. Min Act: -0.0000

Data Index: 80173 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8424. Min Act: -0.0000

Data Index: 878517 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.8386. Min Act: -0.0000

Data Index: 536395 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.5525. Min Act: -0.0000

Data Index: 847554 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1058068 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.6097. Min Act: -0.0000

Data Index: 336487 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.6220. Min Act: -0.0000

Data Index: 1043855 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.5119. Min Act: -0.0000

Data Index: 129015 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1120507 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.3257. Min Range: -2.3257

Max Act: 1.5179. Min Act: -0.0000

Data Index: 228934 (C4 (Web Text))

Max Activating Token Index: 496