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

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

Neuron 2352 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: 1.5918. Min Range: -1.5918

Max Act: 1.5918. Min Act: -0.0000

Data Index: 51267 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5599. Min Act: -0.0000

Data Index: 52926 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.5514. Min Act: -0.0000

Data Index: 738095 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.3210. Min Act: -0.0000

Data Index: 372679 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.3975. Min Act: -0.0000

Data Index: 1318325 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.4711. Min Act: -0.0000

Data Index: 653432 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2794. Min Act: -0.0000

Data Index: 238266 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2653. Min Act: -0.0000

Data Index: 1185511 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1054550 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2988. Min Act: -0.0000

Data Index: 649968 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2823. Min Act: -0.0000

Data Index: 838361 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.1828. Min Act: -0.0000

Data Index: 770588 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2511. Min Act: -0.0000

Data Index: 153321 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2353. Min Act: -0.0000

Data Index: 909006 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1316457 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.1888. Min Act: -0.0000

Data Index: 778864 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1003053 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.1047. Min Act: -0.0000

Data Index: 940251 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1105983 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.5918. Min Range: -1.5918

Max Act: 1.0936. Min Act: -0.0000

Data Index: 485455 (C4 (Web Text))

Max Activating Token Index: 590