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

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

Neuron 2658 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: 2.0421. Min Range: -2.0421

Max Act: 1.9747. Min Act: -0.0000

Data Index: 1004427 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 2.0421. Min Range: -2.0421

Max Act: 2.0421. Min Act: -0.0000

Data Index: 686368 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.9186. Min Act: -0.0000

Data Index: 492321 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.8151. Min Act: -0.0000

Data Index: 271954 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.8602. Min Act: -0.0000

Data Index: 169549 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7506. Min Act: -0.0000

Data Index: 703955 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7799. Min Act: -0.0000

Data Index: 1135371 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7560. Min Act: -0.0000

Data Index: 649886 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7567. Min Act: -0.0000

Data Index: 8536 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7316. Min Act: -0.0000

Data Index: 973785 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.6414. Min Act: -0.0000

Data Index: 928447 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7164. Min Act: -0.0000

Data Index: 120314 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7087. Min Act: -0.0000

Data Index: 763713 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.6704. Min Act: -0.0000

Data Index: 811189 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.6578. Min Act: -0.0000

Data Index: 882810 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1199118 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.5433. Min Act: -0.0000

Data Index: 540359 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.7164. Min Act: -0.0000

Data Index: 38677 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.5086. Min Act: -0.0000

Data Index: 168907 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 2.0421. Min Range: -2.0421

Max Act: 1.5835. Min Act: -0.0000

Data Index: 935211 (C4 (Web Text))

Max Activating Token Index: 425