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

Dataset: The Pile

Neuron 2474 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: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1669596 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1409921 (The Pile)

Max Activating Token Index: 785

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5780. Min Act: -0.0000

Data Index: 819351 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5850. Min Act: -0.0000

Data Index: 334591 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6305. Min Act: -0.0000

Data Index: 421140 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5405. Min Act: -0.0000

Data Index: 422770 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5420. Min Act: -0.0000

Data Index: 906241 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1473037 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5463. Min Act: -0.0000

Data Index: 597849 (The Pile)

Max Activating Token Index: 868

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1773927 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5172. Min Act: -0.0000

Data Index: 576522 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1184736 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1486805 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1302242 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6185. Min Act: -0.0000

Data Index: 470414 (The Pile)

Max Activating Token Index: 886

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1515433 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5258. Min Act: -0.0000

Data Index: 173663 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1546594 (The Pile)

Max Activating Token Index: 952

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1339468 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1271404 (The Pile)

Max Activating Token Index: 940