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

Dataset: The Pile

Neuron 2998 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 238685 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 69397 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 555344 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 217074 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1343884 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1411445 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 354007 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 235804 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 416394 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 766737 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 106773 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 668416 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 678256 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 625143 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1941195 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 377607 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1400606 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1333319 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 705676 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 921072 (The Pile)

Max Activating Token Index: 1