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

Dataset: The Pile

Neuron 2602 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: 3.2837. Min Range: -3.2837

Max Act: 3.2837. Min Act: -0.0000

Data Index: 1820077 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.6297. Min Act: -0.0000

Data Index: 1119505 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.5586. Min Act: -0.0000

Data Index: 1115373 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.3812. Min Act: -0.0000

Data Index: 136180 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.1712. Min Act: -0.0000

Data Index: 315228 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.3381. Min Act: -0.0000

Data Index: 1305145 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.0846. Min Act: -0.0000

Data Index: 1452612 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.2838. Min Act: -0.0000

Data Index: 1394923 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.1422. Min Act: -0.0000

Data Index: 930068 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.2459. Min Act: -0.0000

Data Index: 1723644 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.9839. Min Act: -0.0000

Data Index: 925356 (The Pile)

Max Activating Token Index: 473

Text #11

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.9587. Min Act: -0.0000

Data Index: 1586659 (The Pile)

Max Activating Token Index: 531

Text #12

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.9581. Min Act: -0.0000

Data Index: 877265 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.0252. Min Act: -0.0000

Data Index: 415816 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.0284. Min Act: -0.0000

Data Index: 169182 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.0109. Min Act: -0.0000

Data Index: 1140415 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 3.2837. Min Range: -3.2837

Max Act: 2.1092. Min Act: -0.0000

Data Index: 1753582 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.9726. Min Act: -0.0000

Data Index: 248113 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.8546. Min Act: -0.0000

Data Index: 1129851 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 3.2837. Min Range: -3.2837

Max Act: 1.8465. Min Act: -0.0000

Data Index: 1977534 (The Pile)

Max Activating Token Index: 79