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

Dataset: The Pile

Neuron 1828 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: 1.4735. Min Range: -1.4735

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1883714 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.4320. Min Act: -0.0000

Data Index: 1457756 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1469592 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1678201 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1862703 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1729826 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.3656. Min Act: -0.0000

Data Index: 142464 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2732. Min Act: -0.0000

Data Index: 554940 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1742993 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1591604 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2683. Min Act: -0.0000

Data Index: 594141 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.1847. Min Act: -0.0000

Data Index: 926751 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1182776 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1635191 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0101. Min Act: -0.0000

Data Index: 884314 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0847. Min Act: -0.0000

Data Index: 683774 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0824. Min Act: -0.0000

Data Index: 186539 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0114. Min Act: -0.0000

Data Index: 124481 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0588. Min Act: -0.0000

Data Index: 793261 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 1.4735. Min Range: -1.4735

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1334346 (The Pile)

Max Activating Token Index: 715