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

Dataset: The Pile

Neuron 507 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.7829. Min Act: -0.0000

Data Index: 949236 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1237338 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.6043. Min Act: -0.0000

Data Index: 544006 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.6468. Min Act: -0.0000

Data Index: 887452 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4766. Min Act: -0.0000

Data Index: 122899 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1897727 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4672. Min Act: -0.0000

Data Index: 1533813 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4581. Min Act: -0.0000

Data Index: 1218071 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1307443 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1625120 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3268. Min Act: -0.0000

Data Index: 840895 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1731436 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2494. Min Act: -0.0000

Data Index: 464823 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1861111 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3372. Min Act: -0.0000

Data Index: 444114 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3065. Min Act: -0.0000

Data Index: 233508 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3038. Min Act: -0.0000

Data Index: 128774 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2664. Min Act: -0.0000

Data Index: 877347 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1409748 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 1.7829. Min Range: -1.7829

Max Act: 1.2387. Min Act: -0.0000

Data Index: 559634 (The Pile)

Max Activating Token Index: 90