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

Dataset: The Pile

Neuron 3960 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0127. Min Range: -1.0127

Max Act: 1.0127. Min Act: -0.0000

Data Index: 647408 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1839993 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1373484 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1711793 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1431348 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9197. Min Act: -0.0000

Data Index: 909802 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1169405 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1930856 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8897. Min Act: -0.0000

Data Index: 712046 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8796. Min Act: -0.0000

Data Index: 269979 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.9067. Min Act: -0.0000

Data Index: 987070 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1648382 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1143974 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1475069 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8312. Min Act: -0.0000

Data Index: 919517 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1818809 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8351. Min Act: -0.0000

Data Index: 577067 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1201407 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1475710 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 1.0127. Min Range: -1.0127

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1447749 (The Pile)

Max Activating Token Index: 738