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

Dataset: The Pile

Neuron 2598 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9974. Min Range: -5.9974

Max Act: 5.9974. Min Act: -0.0000

Data Index: 1929618 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.6875. Min Act: -0.0000

Data Index: 18846 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 5.9974. Min Range: -5.9974

Max Act: 5.0902. Min Act: -0.0000

Data Index: 485189 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.5305. Min Act: -0.0000

Data Index: 1029948 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.2426. Min Act: -0.0000

Data Index: 579908 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.0020. Min Act: -0.0000

Data Index: 1498023 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.0900. Min Act: -0.0000

Data Index: 960560 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.0627. Min Act: -0.0000

Data Index: 1567195 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.0601. Min Act: -0.0000

Data Index: 235745 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.0677. Min Act: -0.0000

Data Index: 1859896 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.6487. Min Act: -0.0000

Data Index: 1615791 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 5.9974. Min Range: -5.9974

Max Act: 4.4456. Min Act: -0.0000

Data Index: 1154757 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.9150. Min Act: -0.0000

Data Index: 1136856 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.8030. Min Act: -0.0000

Data Index: 455331 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.5454. Min Act: -0.0000

Data Index: 1775700 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.5424. Min Act: -0.0000

Data Index: 1095148 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.3724. Min Act: -0.0000

Data Index: 1108333 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.6605. Min Act: -0.0000

Data Index: 264083 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.7765. Min Act: -0.0000

Data Index: 1823490 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 5.9974. Min Range: -5.9974

Max Act: 3.2252. Min Act: -0.0000

Data Index: 542064 (The Pile)

Max Activating Token Index: 949