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

Dataset: The Pile

Neuron 1311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.2939. Min Act: -0.0000

Data Index: 443775 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.1584. Min Act: -0.0000

Data Index: 718436 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.0082. Min Act: -0.0000

Data Index: 126711 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.3008. Min Range: -1.3008

Max Act: 1.3008. Min Act: -0.0000

Data Index: 667389 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9430. Min Act: -0.0000

Data Index: 920902 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8144. Min Act: -0.0000

Data Index: 124923 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8928. Min Act: -0.0000

Data Index: 928964 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1087439 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8973. Min Act: -0.0000

Data Index: 382239 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9527. Min Act: -0.0000

Data Index: 870932 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1940537 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1821879 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1137670 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.9374. Min Act: -0.0000

Data Index: 897082 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1945721 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8389. Min Act: -0.0000

Data Index: 133822 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8645. Min Act: -0.0000

Data Index: 308734 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1108653 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.8871. Min Act: -0.0000

Data Index: 603348 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 1.3008. Min Range: -1.3008

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1935675 (The Pile)

Max Activating Token Index: 511