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

Dataset: The Pile

Neuron 1598 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: 0.7130. Min Range: -0.7130

Max Act: 0.7130. Min Act: -0.0000

Data Index: 502074 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1297416 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4581. Min Act: -0.0000

Data Index: 834319 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1375009 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1154670 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4304. Min Act: -0.0000

Data Index: 121740 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1591409 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1449794 (The Pile)

Max Activating Token Index: 542

Text #8

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1855428 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4288. Min Act: -0.0000

Data Index: 782286 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1901200 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1434651 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1110709 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1988324 (The Pile)

Max Activating Token Index: 821

Text #14

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1974916 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3538. Min Act: -0.0000

Data Index: 192796 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3139. Min Act: -0.0000

Data Index: 335351 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3494. Min Act: -0.0000

Data Index: 442795 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1296302 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.3213. Min Act: -0.0000

Data Index: 892254 (The Pile)

Max Activating Token Index: 747