Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3265 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4591. Min Act: -0.0000

Data Index: 298500 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4534. Min Act: -0.0000

Data Index: 330983 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1472975 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4273. Min Act: -0.0000

Data Index: 959819 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4127. Min Act: -0.0000

Data Index: 815515 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1100914 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4155. Min Act: -0.0000

Data Index: 708594 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4107. Min Act: -0.0000

Data Index: 857570 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4125. Min Act: -0.0000

Data Index: 83857 (The Pile)

Max Activating Token Index: 944

Text #9

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1929870 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4183. Min Act: 0.0000

Data Index: 214480 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4404. Min Act: 0.0000

Data Index: 417596 (The Pile)

Max Activating Token Index: 685

Text #12

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1596071 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4072. Min Act: -0.0000

Data Index: 576655 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1559222 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3772. Min Act: -0.0000

Data Index: 830807 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1622331 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.4013. Min Act: -0.0000

Data Index: 219944 (The Pile)

Max Activating Token Index: 975

Text #18

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1277547 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.4618. Min Range: -0.4618

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1998373 (The Pile)

Max Activating Token Index: 701