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

Dataset: The Pile

Neuron 1830 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: 1.9203. Min Range: -1.9203

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1240372 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1897034 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.7831. Min Act: -0.0000

Data Index: 794556 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1422321 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5457. Min Act: -0.0000

Data Index: 137158 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5756. Min Act: -0.0000

Data Index: 52572 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1658079 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1101135 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1741532 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1639382 (The Pile)

Max Activating Token Index: 755

Text #10

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4120. Min Act: -0.0000

Data Index: 976523 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5789. Min Act: -0.0000

Data Index: 883067 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1282306 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4927. Min Act: -0.0000

Data Index: 1418751 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4149. Min Act: -0.0000

Data Index: 706991 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5655. Min Act: -0.0000

Data Index: 148582 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4723. Min Act: -0.0000

Data Index: 461102 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4632. Min Act: -0.0000

Data Index: 1458336 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.5373. Min Act: -0.0000

Data Index: 579087 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 1.9203. Min Range: -1.9203

Max Act: 1.4202. Min Act: -0.0000

Data Index: 601835 (The Pile)

Max Activating Token Index: 899