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

Dataset: The Pile

Neuron 336 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: 1.1864. Min Range: -1.1864

Max Act: 1.1864. Min Act: -0.0000

Data Index: 308499 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 1.1864. Min Range: -1.1864

Max Act: 1.1032. Min Act: -0.0000

Data Index: 645061 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 1.1864. Min Range: -1.1864

Max Act: 1.1312. Min Act: 0.0000

Data Index: 109894 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 1.1864. Min Range: -1.1864

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1261501 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9706. Min Act: -0.0000

Data Index: 511697 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1243837 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1062526 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1664698 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9366. Min Act: -0.0000

Data Index: 47187 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1499656 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9414. Min Act: -0.0000

Data Index: 152265 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8127. Min Act: -0.0000

Data Index: 628416 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1239586 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1033191 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1400301 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1381895 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1576379 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.9080. Min Act: -0.0000

Data Index: 268546 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.8134. Min Act: -0.0000

Data Index: 5088 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1027697 (The Pile)

Max Activating Token Index: 388