Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1317 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0758. Min Act: -0.0000

Data Index: 1521837 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1118398 (The Pile)

Max Activating Token Index: 641

Text #2

Max Range: 1.1514. Min Range: -1.1514

Max Act: 1.1514. Min Act: -0.0000

Data Index: 33524 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8420. Min Act: -0.0000

Data Index: 965407 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8676. Min Act: -0.0000

Data Index: 40702 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1856527 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8077. Min Act: -0.0000

Data Index: 474587 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1343807 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1401558 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7953. Min Act: -0.0000

Data Index: 195667 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7643. Min Act: -0.0000

Data Index: 747691 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7632. Min Act: -0.0000

Data Index: 295316 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1036534 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7034. Min Act: -0.0000

Data Index: 961823 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1324317 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1350985 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6689. Min Act: -0.0000

Data Index: 415304 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1245922 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1195147 (The Pile)

Max Activating Token Index: 691

Text #19

Max Range: 1.1514. Min Range: -1.1514

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1509070 (The Pile)

Max Activating Token Index: 335