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

Dataset: The Pile

Neuron 3211 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: 1.1392. Min Range: -1.1392

Max Act: 1.0104. Min Act: -0.0000

Data Index: 1739607 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1392. Min Act: -0.0000

Data Index: 187021 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1031225 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8921. Min Act: -0.0000

Data Index: 591790 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8595. Min Act: -0.0000

Data Index: 562751 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1822326 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1233034 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7412. Min Act: -0.0000

Data Index: 650435 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8389. Min Act: -0.0000

Data Index: 323018 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1159515 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1258739 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7096. Min Act: -0.0000

Data Index: 137254 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1717885 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1844101 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1023773 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7300. Min Act: -0.0000

Data Index: 160148 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6951. Min Act: -0.0000

Data Index: 312036 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1401706 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7599. Min Act: -0.0000

Data Index: 229998 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7860. Min Act: -0.0000

Data Index: 391642 (The Pile)

Max Activating Token Index: 15