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

Dataset: The Pile

Neuron 2078 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.7416. Min Act: -0.0000

Data Index: 971418 (The Pile)

Max Activating Token Index: 481

Text #1

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1793560 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1672081 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1833873 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1802662 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1822232 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1398350 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1201825 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.6033. Min Act: -0.0000

Data Index: 873351 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4901. Min Act: -0.0000

Data Index: 667110 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1676605 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1525132 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1066204 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4663. Min Act: -0.0000

Data Index: 152650 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4688. Min Act: -0.0000

Data Index: 845357 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1866550 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1044187 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1572792 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4525. Min Act: -0.0000

Data Index: 187001 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.7416. Min Range: -0.7416

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1416758 (The Pile)

Max Activating Token Index: 583