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

Dataset: The Pile

Neuron 3085 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: 0.7045. Min Range: -0.7045

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1734469 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.6492. Min Act: -0.0000

Data Index: 310585 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.6014. Min Act: -0.0000

Data Index: 684574 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5494. Min Act: -0.0000

Data Index: 466192 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1507701 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5385. Min Act: -0.0000

Data Index: 5393 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1166792 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4612. Min Act: -0.0000

Data Index: 193543 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1460248 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1021218 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4074. Min Act: -0.0000

Data Index: 956639 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1405206 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1333229 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4875. Min Act: -0.0000

Data Index: 969684 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5016. Min Act: -0.0000

Data Index: 175843 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5178. Min Act: -0.0000

Data Index: 970161 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4637. Min Act: -0.0000

Data Index: 388940 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5115. Min Act: -0.0000

Data Index: 434022 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1604104 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 0.7045. Min Range: -0.7045

Max Act: 0.4680. Min Act: -0.0000

Data Index: 69284 (The Pile)

Max Activating Token Index: 555