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

Dataset: The Pile

Neuron 872 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: 3.6776. Min Range: -3.6776

Max Act: 3.6776. Min Act: -0.0000

Data Index: 1054186 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.3603. Min Act: -0.0000

Data Index: 425702 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.5424. Min Act: -0.0000

Data Index: 464379 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.1472. Min Act: -0.0000

Data Index: 1014700 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.1829. Min Act: -0.0000

Data Index: 1336753 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0165. Min Act: -0.0000

Data Index: 1565375 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0683. Min Act: -0.0000

Data Index: 350306 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.2106. Min Act: -0.0000

Data Index: 1546092 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.2128. Min Act: -0.0000

Data Index: 617763 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0193. Min Act: -0.0000

Data Index: 177754 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.9556. Min Act: -0.0000

Data Index: 281439 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.7991. Min Act: -0.0000

Data Index: 1410917 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.8682. Min Act: -0.0000

Data Index: 452046 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0308. Min Act: -0.0000

Data Index: 621646 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.8172. Min Act: -0.0000

Data Index: 1641466 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.8199. Min Act: -0.0000

Data Index: 266499 (The Pile)

Max Activating Token Index: 738

Text #16

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.9492. Min Act: -0.0000

Data Index: 322151 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.6384. Min Act: -0.0000

Data Index: 1332265 (The Pile)

Max Activating Token Index: 472

Text #18

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.7530. Min Act: -0.0000

Data Index: 359135 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.7303. Min Act: -0.0000

Data Index: 1800367 (The Pile)

Max Activating Token Index: 397