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

Dataset: The Pile

Neuron 1492 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: 1.0159. Min Range: -1.0159

Max Act: 0.9302. Min Act: -0.0000

Data Index: 318521 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.9518. Min Act: -0.0000

Data Index: 647931 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 1.0159. Min Range: -1.0159

Max Act: 1.0159. Min Act: -0.0000

Data Index: 641163 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8238. Min Act: -0.0000

Data Index: 114446 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8113. Min Act: -0.0000

Data Index: 97082 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8079. Min Act: -0.0000

Data Index: 528884 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8237. Min Act: -0.0000

Data Index: 847081 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7512. Min Act: -0.0000

Data Index: 888303 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1956645 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1166756 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7481. Min Act: -0.0000

Data Index: 884707 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1621569 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1030314 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1910176 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1026603 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6555. Min Act: -0.0000

Data Index: 266846 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1624263 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1868268 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1547996 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.0159. Min Range: -1.0159

Max Act: 0.6072. Min Act: -0.0000

Data Index: 970180 (The Pile)

Max Activating Token Index: 523