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

Dataset: The Pile

Neuron 194 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: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0000

Data Index: 395002 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5580. Min Act: -0.0000

Data Index: 964033 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1660998 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5352. Min Act: -0.0000

Data Index: 95316 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1580656 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5171. Min Act: -0.0000

Data Index: 384316 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5285. Min Act: -0.0000

Data Index: 371566 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5249. Min Act: -0.0000

Data Index: 316107 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1749235 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5159. Min Act: -0.0000

Data Index: 746890 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5136. Min Act: -0.0000

Data Index: 363124 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5012. Min Act: -0.0000

Data Index: 988039 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5175. Min Act: -0.0000

Data Index: 593229 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4808. Min Act: -0.0000

Data Index: 786574 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1409155 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5087. Min Act: -0.0000

Data Index: 469887 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4929. Min Act: -0.0000

Data Index: 131339 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1854097 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1494309 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5293. Min Act: -0.0000

Data Index: 247665 (The Pile)

Max Activating Token Index: 915