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

Dataset: The Pile

Neuron 3639 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1911539 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3373. Min Act: -0.0000

Data Index: 136100 (The Pile)

Max Activating Token Index: 17

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1782694 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1047. Min Act: -0.0000

Data Index: 883785 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1707613 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1714028 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0963. Min Act: -0.0000

Data Index: 99112 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0837. Min Act: -0.0000

Data Index: 288772 (The Pile)

Max Activating Token Index: 342

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1455. Min Act: -0.0000

Data Index: 332364 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0728. Min Act: -0.0000

Data Index: 180062 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0713. Min Act: -0.0000

Data Index: 161997 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1132. Min Act: -0.0000

Data Index: 291755 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1186639 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1354489 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0490. Min Act: 0.0000

Data Index: 277596 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1826839 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1719761 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0216. Min Act: -0.0000

Data Index: 92811 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1051366 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 0.9681. Min Act: -0.0000

Data Index: 307718 (The Pile)

Max Activating Token Index: 573