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

Dataset: The Pile

Neuron 1377 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: 0.5528. Min Range: -0.5528

Max Act: 0.5528. Min Act: -0.0000

Data Index: 431988 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5223. Min Act: -0.0000

Data Index: 630475 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5158. Min Act: -0.0000

Data Index: 511928 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5148. Min Act: -0.0000

Data Index: 975027 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1256182 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1385685 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5145. Min Act: -0.0000

Data Index: 456712 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.5171. Min Act: -0.0000

Data Index: 972840 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4806. Min Act: -0.0000

Data Index: 697657 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1370965 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4642. Min Act: -0.0000

Data Index: 519502 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1122413 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1739247 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1437754 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1405529 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4738. Min Act: -0.0000

Data Index: 956401 (The Pile)

Max Activating Token Index: 626

Text #16

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4367. Min Act: -0.0000

Data Index: 411553 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4331. Min Act: -0.0000

Data Index: 570464 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4359. Min Act: -0.0000

Data Index: 888265 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 0.5528. Min Range: -0.5528

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1302681 (The Pile)

Max Activating Token Index: 153