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

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

Neuron 2808 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1245404 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1084614 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.1128. Min Act: -0.0000

Data Index: 325899 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.2200. Min Range: -1.2200

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1303576 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1433 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9513. Min Act: -0.0000

Data Index: 960393 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9580. Min Act: -0.0000

Data Index: 215373 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8712. Min Act: -0.0000

Data Index: 658357 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9293. Min Act: -0.0000

Data Index: 979870 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9488. Min Act: -0.0000

Data Index: 853516 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8781. Min Act: -0.0000

Data Index: 886711 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.9267. Min Act: -0.0000

Data Index: 568679 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8234. Min Act: -0.0000

Data Index: 804099 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8354. Min Act: -0.0000

Data Index: 601457 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8015. Min Act: -0.0000

Data Index: 486217 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.7781. Min Act: -0.0000

Data Index: 781186 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.8247. Min Act: -0.0000

Data Index: 358346 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.7937. Min Act: -0.0000

Data Index: 385574 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.7997. Min Act: -0.0000

Data Index: 694873 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.2200. Min Range: -1.2200

Max Act: 0.7863. Min Act: -0.0000

Data Index: 453452 (C4 (Web Text))

Max Activating Token Index: 473