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

Dataset: The Pile

Neuron 4579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.3761. Min Act: -0.0000

Data Index: 1386033 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.0310. Min Act: -0.0000

Data Index: 1552556 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.3030. Min Act: -0.0000

Data Index: 1142507 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.0267. Min Act: -0.0000

Data Index: 1185587 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.9497. Min Act: -0.0000

Data Index: 472772 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.0690. Min Act: -0.0000

Data Index: 974045 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1303326 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.8430. Min Act: -0.0000

Data Index: 321653 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.8368. Min Act: -0.0000

Data Index: 164308 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.6366. Min Act: -0.0000

Data Index: 1240535 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5907. Min Act: -0.0000

Data Index: 1063539 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5937. Min Act: -0.0000

Data Index: 101200 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1409195 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5203. Min Act: -0.0000

Data Index: 1794836 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5101. Min Act: -0.0000

Data Index: 94645 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3465. Min Act: -0.0000

Data Index: 1314360 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3262. Min Act: -0.0000

Data Index: 1347994 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3025. Min Act: -0.0000

Data Index: 1296026 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4395. Min Act: -0.0000

Data Index: 860064 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5325. Min Act: -0.0000

Data Index: 864617 (The Pile)

Max Activating Token Index: 2