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

Dataset: The Pile

Neuron 3183 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: 0.6768. Min Range: -0.6768

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1318311 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1585722 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4611. Min Act: -0.0000

Data Index: 959512 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4471. Min Act: -0.0000

Data Index: 144007 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4313. Min Act: 0.0000

Data Index: 930025 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4063. Min Act: 0.0000

Data Index: 734171 (The Pile)

Max Activating Token Index: 908

Text #6

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1039871 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4126. Min Act: 0.0000

Data Index: 1220355 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4376. Min Act: -0.0000

Data Index: 746485 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4207. Min Act: -0.0000

Data Index: 478851 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4195. Min Act: -0.0000

Data Index: 351092 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4052. Min Act: -0.0000

Data Index: 257532 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1124926 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4029. Min Act: -0.0000

Data Index: 766363 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4043. Min Act: -0.0000

Data Index: 344517 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4180. Min Act: -0.0000

Data Index: 711793 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3816. Min Act: -0.0000

Data Index: 741754 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1306964 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3714. Min Act: -0.0000

Data Index: 954775 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3736. Min Act: -0.0000

Data Index: 630851 (The Pile)

Max Activating Token Index: 873