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

Dataset: The Pile

Neuron 2157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7245. Min Act: 0.0000

Data Index: 1247653 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1469262 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1867250 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7119. Min Act: -0.0000

Data Index: 585375 (The Pile)

Max Activating Token Index: 684

Text #4

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1368953 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1819710 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5963. Min Act: -0.0000

Data Index: 197014 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5998. Min Act: -0.0000

Data Index: 929515 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5925. Min Act: -0.0000

Data Index: 29643 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1095196 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1479501 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6531. Min Act: -0.0000

Data Index: 812517 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1951113 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5942. Min Act: -0.0000

Data Index: 268716 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1331475 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5818. Min Act: -0.0000

Data Index: 873721 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5770. Min Act: -0.0000

Data Index: 579578 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.7157. Min Act: -0.0001

Data Index: 127543 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.4530. Min Act: 0.0000

Data Index: 1050977 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.7496. Min Range: -0.7496

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1495036 (The Pile)

Max Activating Token Index: 126