Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5509 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4452. Min Range: -1.4452

Max Act: 1.4452. Min Act: -0.0000

Data Index: 388843 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 1.4452. Min Range: -1.4452

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1125735 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9819. Min Act: -0.0000

Data Index: 267545 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.4452. Min Range: -1.4452

Max Act: 1.0132. Min Act: -0.0000

Data Index: 991892 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9864. Min Act: -0.0000

Data Index: 540418 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1179713 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.8465. Min Act: -0.0000

Data Index: 649115 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9795. Min Act: -0.0000

Data Index: 509459 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 1.4452. Min Range: -1.4452

Max Act: 1.1021. Min Act: -0.0000

Data Index: 262157 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1269953 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9411. Min Act: -0.0000

Data Index: 465656 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1166865 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9576. Min Act: -0.0000

Data Index: 599510 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1046553 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.8690. Min Act: -0.0000

Data Index: 339060 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9089. Min Act: -0.0000

Data Index: 600751 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.9196. Min Act: -0.0000

Data Index: 944553 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.8417. Min Act: -0.0000

Data Index: 515046 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.8433. Min Act: -0.0000

Data Index: 889280 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.4452. Min Range: -1.4452

Max Act: 0.8999. Min Act: -0.0000

Data Index: 162458 (C4 (Web Text))

Max Activating Token Index: 148