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

Dataset: The Pile

Neuron 1714 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: 0.9497. Min Range: -0.9497

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1788772 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1083867 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1129615 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8734. Min Act: -0.0000

Data Index: 337949 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1405404 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7137. Min Act: -0.0000

Data Index: 274801 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7358. Min Act: -0.0000

Data Index: 180509 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1400293 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1445243 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1151253 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1257983 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1101479 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.7754. Min Act: -0.0000

Data Index: 16223 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1625452 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6289. Min Act: -0.0000

Data Index: 771998 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1376926 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6229. Min Act: -0.0000

Data Index: 792351 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1774017 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1474815 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.9497. Min Range: -0.9497

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1687052 (The Pile)

Max Activating Token Index: 901