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

Dataset: The Pile

Neuron 2643 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: 1.4388. Min Range: -1.4388

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1511229 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2208. Min Act: -0.0000

Data Index: 220187 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.9902. Min Act: -0.0000

Data Index: 954753 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1859319 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.8899. Min Act: -0.0000

Data Index: 64620 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.8644. Min Act: -0.0000

Data Index: 445596 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1784154 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7773. Min Act: -0.0000

Data Index: 877639 (The Pile)

Max Activating Token Index: 277

Text #8

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.6670. Min Act: -0.0000

Data Index: 157725 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1553836 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1993382 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1672339 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1818536 (The Pile)

Max Activating Token Index: 859

Text #13

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1295389 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1767580 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1651833 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7077. Min Act: -0.0000

Data Index: 185514 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1581047 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.6379. Min Act: -0.0000

Data Index: 17633 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.4388. Min Range: -1.4388

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1695811 (The Pile)

Max Activating Token Index: 97