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

Dataset: The Pile

Neuron 4488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1631316 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1608. Min Act: -0.0000

Data Index: 749571 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1015784 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1423. Min Act: -0.0000

Data Index: 858554 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1426. Min Act: -0.0000

Data Index: 698083 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1627592 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1939829 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1380. Min Act: -0.0000

Data Index: 455795 (The Pile)

Max Activating Token Index: 790

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1474767 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1332. Min Act: -0.0000

Data Index: 969486 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1552806 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1396. Min Act: -0.0000

Data Index: 174716 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1634081 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1370. Min Act: -0.0000

Data Index: 543723 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1360. Min Act: -0.0000

Data Index: 665681 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1285. Min Act: -0.0000

Data Index: 134828 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1799570 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1346151 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1832547 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1249. Min Act: -0.0000

Data Index: 386972 (The Pile)

Max Activating Token Index: 398