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

Dataset: The Pile

Neuron 2408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1347569 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1240186 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.4470. Min Act: -0.0000

Data Index: 829942 (The Pile)

Max Activating Token Index: 609

Text #3

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.4214. Min Act: -0.0000

Data Index: 750266 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2410. Min Act: -0.0000

Data Index: 752487 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2455. Min Act: -0.0000

Data Index: 32398 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0786. Min Act: -0.0000

Data Index: 70962 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.2720. Min Act: -0.0000

Data Index: 859651 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1343905 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0577. Min Act: -0.0000

Data Index: 720775 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1013. Min Act: -0.0000

Data Index: 317071 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1465095 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1861046 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.1149. Min Act: -0.0000

Data Index: 139009 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9878. Min Act: 0.0000

Data Index: 374954 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0836. Min Act: -0.0000

Data Index: 664605 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1003157 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1063560 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 1.5660. Min Range: -1.5660

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1393411 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.5660. Min Range: -1.5660

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1052643 (The Pile)

Max Activating Token Index: 746