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

Dataset: The Pile

Neuron 546 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.0324. Min Act: -0.0000

Data Index: 1866212 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.1441. Min Act: -0.0000

Data Index: 1956869 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.3511. Min Act: -0.0000

Data Index: 1873568 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.1723. Min Act: -0.0000

Data Index: 1244654 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.2264. Min Act: -0.0000

Data Index: 694003 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.2214. Min Act: -0.0000

Data Index: 561306 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.1964. Min Act: -0.0000

Data Index: 1084820 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.7271. Min Act: -0.0000

Data Index: 1042020 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.5321. Min Act: -0.0000

Data Index: 181499 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.4290. Min Act: -0.0000

Data Index: 787608 (The Pile)

Max Activating Token Index: 588

Text #10

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.8937. Min Act: -0.0000

Data Index: 1634995 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.1695. Min Act: -0.0000

Data Index: 281187 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.7456. Min Act: -0.0000

Data Index: 1258893 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.8880. Min Act: -0.0000

Data Index: 859009 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.9362. Min Act: -0.0000

Data Index: 1834683 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.8932. Min Act: -0.0000

Data Index: 428424 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.0877. Min Act: -0.0000

Data Index: 313493 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.9457. Min Act: -0.0000

Data Index: 1823389 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 5.4290. Min Range: -5.4290

Max Act: 4.8893. Min Act: -0.0000

Data Index: 1579939 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 5.4290. Min Range: -5.4290

Max Act: 5.0962. Min Act: -0.0000

Data Index: 77979 (The Pile)

Max Activating Token Index: 707