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

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

Neuron 455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.2164. Min Act: -0.0000

Data Index: 595250 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 2.2267. Min Range: -2.2267

Max Act: 2.2267. Min Act: -0.0000

Data Index: 496262 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.8249. Min Act: -0.0000

Data Index: 248684 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.9972. Min Act: -0.0000

Data Index: 78791 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.7769. Min Act: -0.0000

Data Index: 578883 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.4874. Min Act: -0.0000

Data Index: 571229 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.4818. Min Act: -0.0000

Data Index: 264177 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.6394. Min Act: -0.0000

Data Index: 391959 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3672. Min Act: -0.0000

Data Index: 799890 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.2421. Min Act: -0.0000

Data Index: 426837 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1176300 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3390. Min Act: -0.0000

Data Index: 1274998 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.4836. Min Act: -0.0000

Data Index: 1251301 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.2375. Min Act: -0.0000

Data Index: 220631 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1330492 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1335503 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3181. Min Act: -0.0000

Data Index: 1199852 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.1751. Min Act: -0.0000

Data Index: 286902 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3865. Min Act: -0.0000

Data Index: 519215 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.2267. Min Range: -2.2267

Max Act: 1.3097. Min Act: -0.0000

Data Index: 137326 (C4 (Web Text))

Max Activating Token Index: 488