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

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

Neuron 4310 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1271965 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6873. Min Act: -0.0000

Data Index: 1043891 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.6645. Min Act: -0.0000

Data Index: 872371 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5314. Min Act: -0.0000

Data Index: 1286050 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5774. Min Act: -0.0000

Data Index: 778547 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.5125. Min Act: -0.0000

Data Index: 279536 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4694. Min Act: -0.0000

Data Index: 702028 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4541. Min Act: -0.0000

Data Index: 924966 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.4278. Min Act: -0.0000

Data Index: 698736 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.3846. Min Act: -0.0000

Data Index: 109444 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.3028. Min Act: -0.0000

Data Index: 688787 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.3360. Min Act: -0.0000

Data Index: 98582 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.2075. Min Act: -0.0000

Data Index: 366006 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.2721. Min Act: -0.0000

Data Index: 676500 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.3526. Min Act: -0.0000

Data Index: 701025 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.2724. Min Act: -0.0000

Data Index: 978151 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.2537. Min Act: -0.0000

Data Index: 148859 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1181551 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.2912. Min Act: -0.0000

Data Index: 375772 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.7694. Min Range: -1.7694

Max Act: 1.3340. Min Act: -0.0000

Data Index: 346729 (C4 (Web Text))

Max Activating Token Index: 627