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

Dataset: The Pile

Neuron 30 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5855. Min Range: -5.5855

Max Act: 5.5855. Min Act: -0.0000

Data Index: 1000880 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.8979. Min Act: -0.0000

Data Index: 1907951 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.6419. Min Act: -0.0000

Data Index: 108334 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.6724. Min Act: -0.0000

Data Index: 829894 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.6176. Min Act: -0.0000

Data Index: 1714288 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.2713. Min Act: -0.0000

Data Index: 734744 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.4300. Min Act: -0.0000

Data Index: 1258393 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 5.5855. Min Range: -5.5855

Max Act: 3.9243. Min Act: -0.0000

Data Index: 1082932 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.2956. Min Act: -0.0000

Data Index: 1545005 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.4284. Min Act: -0.0000

Data Index: 1379601 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.2053. Min Act: -0.0000

Data Index: 749221 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.0426. Min Act: -0.0000

Data Index: 255792 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.0296. Min Act: -0.0000

Data Index: 417079 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.3170. Min Act: -0.0000

Data Index: 702839 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 5.5855. Min Range: -5.5855

Max Act: 3.9214. Min Act: -0.0000

Data Index: 295237 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 5.5855. Min Range: -5.5855

Max Act: 3.9964. Min Act: -0.0000

Data Index: 481145 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.1532. Min Act: -0.0000

Data Index: 401099 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 5.5855. Min Range: -5.5855

Max Act: 3.9489. Min Act: -0.0000

Data Index: 73139 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 5.5855. Min Range: -5.5855

Max Act: 4.2572. Min Act: -0.0000

Data Index: 724451 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 5.5855. Min Range: -5.5855

Max Act: 3.9120. Min Act: -0.0000

Data Index: 740558 (The Pile)

Max Activating Token Index: 111