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

Dataset: The Pile

Neuron 4065 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1684683 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5523. Min Act: -0.0000

Data Index: 915185 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5233. Min Act: -0.0000

Data Index: 840742 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.5906. Min Act: -0.0000

Data Index: 245508 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4283. Min Act: -0.0000

Data Index: 815898 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3293. Min Act: -0.0000

Data Index: 614735 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1545304 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1873714 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4276. Min Act: -0.0000

Data Index: 904976 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3897. Min Act: -0.0000

Data Index: 844551 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1773307 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4480. Min Act: -0.0000

Data Index: 159288 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4090. Min Act: -0.0000

Data Index: 624168 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1557070 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.6057. Min Act: -0.0000

Data Index: 529798 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1090716 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3352. Min Act: -0.0000

Data Index: 81404 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1447802 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1227716 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.6057. Min Range: -0.6057

Max Act: 0.3510. Min Act: -0.0000

Data Index: 904516 (The Pile)

Max Activating Token Index: 849