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

Dataset: The Pile

Neuron 2694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.3441. Min Act: -0.0000

Data Index: 383793 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2353. Min Act: -0.0000

Data Index: 133129 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1113882 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2191. Min Act: -0.0000

Data Index: 908073 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1292857 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1777952 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1973. Min Act: -0.0000

Data Index: 465305 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1762. Min Act: -0.0000

Data Index: 499716 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1760. Min Act: -0.0000

Data Index: 709893 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1564163 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1804. Min Act: -0.0000

Data Index: 46975 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1585. Min Act: -0.0000

Data Index: 751238 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1543502 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1596747 (The Pile)

Max Activating Token Index: 494

Text #14

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1243585 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1449. Min Act: -0.0000

Data Index: 405490 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1493. Min Act: -0.0000

Data Index: 157242 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1500. Min Act: -0.0000

Data Index: 315746 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1539847 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 0.3441. Min Range: -0.3441

Max Act: 0.1501. Min Act: -0.0000

Data Index: 631501 (The Pile)

Max Activating Token Index: 600