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

Dataset: The Pile

Neuron 1690 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: 0.9418. Min Range: -0.9418

Max Act: 0.9418. Min Act: -0.0000

Data Index: 824485 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8669. Min Act: -0.0000

Data Index: 514069 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8870. Min Act: -0.0000

Data Index: 641786 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6690. Min Act: -0.0000

Data Index: 217012 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1083845 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.6684. Min Act: -0.0000

Data Index: 412712 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1552058 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1440371 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5448. Min Act: -0.0000

Data Index: 719161 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5285. Min Act: -0.0000

Data Index: 123247 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5508. Min Act: -0.0000

Data Index: 867694 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5673. Min Act: -0.0000

Data Index: 556686 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5206. Min Act: -0.0000

Data Index: 456628 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5343. Min Act: -0.0000

Data Index: 686174 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5152. Min Act: 0.0000

Data Index: 838262 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5265. Min Act: -0.0000

Data Index: 211501 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1540246 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5125. Min Act: -0.0000

Data Index: 977393 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1282810 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1362633 (The Pile)

Max Activating Token Index: 355