Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 945 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.1940. Min Act: -0.0000

Data Index: 390881 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9655. Min Act: -0.0000

Data Index: 878148 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1777852 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1915543 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9255. Min Act: -0.0000

Data Index: 288558 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 1.1940. Min Range: -1.1940

Max Act: 1.0133. Min Act: -0.0000

Data Index: 327182 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1965141 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8774. Min Act: -0.0000

Data Index: 577747 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1593119 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7986. Min Act: -0.0000

Data Index: 820715 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1403072 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1113278 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1292529 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8327. Min Act: -0.0000

Data Index: 468974 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8063. Min Act: -0.0000

Data Index: 940652 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1808881 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1697930 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8124. Min Act: -0.0000

Data Index: 406312 (The Pile)

Max Activating Token Index: 1006

Text #18

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1542778 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 1.1940. Min Range: -1.1940

Max Act: 0.7946. Min Act: -0.0000

Data Index: 407296 (The Pile)

Max Activating Token Index: 218