Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1613087 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1942501 (The Pile)

Max Activating Token Index: 829

Text #2

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1876763 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1222451 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1379694 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6407. Min Act: -0.0000

Data Index: 314921 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1789790 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6192. Min Act: -0.0000

Data Index: 179872 (The Pile)

Max Activating Token Index: 87

Text #8

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6012. Min Act: -0.0000

Data Index: 83955 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5796. Min Act: -0.0000

Data Index: 864242 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1560072 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1476833 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1923429 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1698054 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1935521 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1016177 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5427. Min Act: -0.0000

Data Index: 309189 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5827. Min Act: -0.0000

Data Index: 961321 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5533. Min Act: -0.0000

Data Index: 583877 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5519. Min Act: -0.0000

Data Index: 975084 (The Pile)

Max Activating Token Index: 679