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

Dataset: The Pile

Neuron 2050 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.2143. Min Act: -0.0000

Data Index: 764618 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 5.2143. Min Range: -5.2143

Max Act: 5.1209. Min Act: -0.0000

Data Index: 1653813 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9050. Min Act: -0.0000

Data Index: 1155051 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8015. Min Act: -0.0000

Data Index: 1119278 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8241. Min Act: -0.0000

Data Index: 1830757 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.8140. Min Act: -0.0000

Data Index: 1393313 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6152. Min Act: -0.0000

Data Index: 574298 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6255. Min Act: -0.0000

Data Index: 749240 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.7842. Min Act: -0.0000

Data Index: 1008766 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6126. Min Act: -0.0000

Data Index: 1892652 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.7693. Min Act: -0.0000

Data Index: 1799169 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.7620. Min Act: -0.0000

Data Index: 985713 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.9349. Min Act: -0.0000

Data Index: 979349 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.5579. Min Act: -0.0000

Data Index: 1632609 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.4797. Min Act: -0.0000

Data Index: 67294 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.4241. Min Act: -0.0000

Data Index: 1883713 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.6187. Min Act: -0.0000

Data Index: 577895 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.5818. Min Act: -0.0000

Data Index: 1220675 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.7387. Min Act: -0.0000

Data Index: 1277057 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 5.2143. Min Range: -5.2143

Max Act: 4.3390. Min Act: -0.0000

Data Index: 1720139 (The Pile)

Max Activating Token Index: 157