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

Dataset: The Pile

Neuron 2628 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: 0.8901. Min Range: -0.8901

Max Act: 0.8209. Min Act: -0.0000

Data Index: 976197 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8394. Min Act: -0.0000

Data Index: 850598 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1503032 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7999. Min Act: -0.0000

Data Index: 386135 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7671. Min Act: -0.0000

Data Index: 275110 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1227752 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1992972 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7792. Min Act: -0.0000

Data Index: 773649 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7532. Min Act: -0.0000

Data Index: 998247 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1118246 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1370778 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1000972 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1910653 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7033. Min Act: -0.0000

Data Index: 66378 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1329387 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7095. Min Act: -0.0000

Data Index: 582226 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7866. Min Act: -0.0000

Data Index: 270253 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7192. Min Act: -0.0000

Data Index: 186398 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1173486 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6796. Min Act: -0.0000

Data Index: 681845 (The Pile)

Max Activating Token Index: 623