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

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

Neuron 2888 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8423. Min Range: -8.8423

Max Act: 8.8423. Min Act: -0.0000

Data Index: 720296 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 8.8423. Min Range: -8.8423

Max Act: 7.3944. Min Act: -0.0000

Data Index: 520945 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 8.8423. Min Range: -8.8423

Max Act: 7.2643. Min Act: -0.0000

Data Index: 851196 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 8.8423. Min Range: -8.8423

Max Act: 6.5809. Min Act: -0.0000

Data Index: 226766 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 8.8423. Min Range: -8.8423

Max Act: 6.5783. Min Act: -0.0000

Data Index: 410027 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 8.8423. Min Range: -8.8423

Max Act: 6.6959. Min Act: -0.0000

Data Index: 1006161 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.9434. Min Act: -0.0000

Data Index: 448979 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.2857. Min Act: -0.0000

Data Index: 1256926 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.6773. Min Act: -0.0000

Data Index: 1233382 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.1607. Min Act: -0.0000

Data Index: 365474 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.4433. Min Act: -0.0000

Data Index: 469090 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.0469. Min Act: -0.0000

Data Index: 151855 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.4523. Min Act: -0.0000

Data Index: 1015360 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.0688. Min Act: -0.0000

Data Index: 882583 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 8.8423. Min Range: -8.8423

Max Act: 4.7066. Min Act: -0.0000

Data Index: 649060 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 8.8423. Min Range: -8.8423

Max Act: 4.6467. Min Act: -0.0000

Data Index: 377507 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.2480. Min Act: -0.0000

Data Index: 95302 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 8.8423. Min Range: -8.8423

Max Act: 4.7605. Min Act: -0.0000

Data Index: 206869 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.1484. Min Act: -0.0000

Data Index: 1087780 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 8.8423. Min Range: -8.8423

Max Act: 5.2265. Min Act: -0.0000

Data Index: 1074282 (C4 (Web Text))

Max Activating Token Index: 560