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

Dataset: The Pile

Neuron 4705 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.3010. Min Act: -0.0000

Data Index: 655129 (The Pile)

Max Activating Token Index: 240

Text #1

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2844. Min Act: -0.0000

Data Index: 980882 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2566. Min Act: -0.0000

Data Index: 546977 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2478. Min Act: -0.0000

Data Index: 872265 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2463. Min Act: -0.0000

Data Index: 295041 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1147545 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2394. Min Act: -0.0000

Data Index: 71163 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1061422 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2188. Min Act: -0.0000

Data Index: 563362 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2154. Min Act: -0.0000

Data Index: 410157 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1681901 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2227. Min Act: -0.0000

Data Index: 4360 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1951679 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2115. Min Act: -0.0000

Data Index: 763462 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2061. Min Act: -0.0000

Data Index: 981399 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1434533 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1583381 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1581563 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1879607 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.3010. Min Range: -0.3010

Max Act: 0.1904. Min Act: -0.0000

Data Index: 959167 (The Pile)

Max Activating Token Index: 617