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

Dataset: The Pile

Neuron 2537 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: 0.5923. Min Range: -0.5923

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1490410 (The Pile)

Max Activating Token Index: 981

Text #1

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5589. Min Act: -0.0000

Data Index: 973466 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5815. Min Act: -0.0000

Data Index: 502538 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5879. Min Act: -0.0000

Data Index: 1167573 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1591604 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5455. Min Act: 0.0000

Data Index: 1849038 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1037573 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1387194 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4830. Min Act: -0.0000

Data Index: 915819 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1058584 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4859. Min Act: -0.0000

Data Index: 356679 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.5154. Min Act: -0.0000

Data Index: 853976 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4605. Min Act: -0.0000

Data Index: 483441 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4512. Min Act: -0.0000

Data Index: 215883 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4706. Min Act: -0.0000

Data Index: 327200 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1584104 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1330151 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1208725 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1256808 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 0.5923. Min Range: -0.5923

Max Act: 0.4193. Min Act: -0.0000

Data Index: 95025 (The Pile)

Max Activating Token Index: 23