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

Dataset: The Pile

Neuron 662 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: 0.6388. Min Range: -0.6388

Max Act: 0.6388. Min Act: 0.0000

Data Index: 1147371 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5377. Min Act: 0.0000

Data Index: 829307 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1349349 (The Pile)

Max Activating Token Index: 341

Text #3

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4892. Min Act: -0.0000

Data Index: 920490 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4457. Min Act: 0.0000

Data Index: 1793449 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1861494 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4957. Min Act: -0.0000

Data Index: 990405 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4441. Min Act: 0.0000

Data Index: 1148552 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4293. Min Act: 0.0000

Data Index: 1687549 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4754. Min Act: 0.0000

Data Index: 352482 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4374. Min Act: -0.0000

Data Index: 675142 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4658. Min Act: -0.0000

Data Index: 543442 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4158. Min Act: -0.0000

Data Index: 248887 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4797. Min Act: -0.0000

Data Index: 622976 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4693. Min Act: -0.0000

Data Index: 323733 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1488383 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1224959 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1780227 (The Pile)

Max Activating Token Index: 770

Text #18

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4461. Min Act: 0.0000

Data Index: 414802 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4541. Min Act: 0.0000

Data Index: 1023058 (The Pile)

Max Activating Token Index: 822