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

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

Neuron 3391 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: 0.8795. Min Range: -0.8795

Max Act: 0.8795. Min Act: -0.0000

Data Index: 486189 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.7510. Min Act: -0.0000

Data Index: 980987 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.7318. Min Act: -0.0000

Data Index: 322791 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1094788 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6337. Min Act: -0.0000

Data Index: 810083 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6634. Min Act: -0.0000

Data Index: 874589 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6559. Min Act: -0.0000

Data Index: 313412 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6178. Min Act: -0.0000

Data Index: 663732 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6213. Min Act: -0.0000

Data Index: 385430 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5968. Min Act: -0.0000

Data Index: 627509 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6159. Min Act: -0.0000

Data Index: 388072 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1225612 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6245. Min Act: -0.0000

Data Index: 239340 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.6170. Min Act: -0.0000

Data Index: 933708 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5988. Min Act: -0.0000

Data Index: 606101 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5396. Min Act: -0.0000

Data Index: 26603 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5954. Min Act: -0.0000

Data Index: 911153 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5698. Min Act: -0.0000

Data Index: 278685 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5708. Min Act: -0.0000

Data Index: 475207 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.8795. Min Range: -0.8795

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1075386 (C4 (Web Text))

Max Activating Token Index: 363