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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4884 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1009484 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5131. Min Act: -0.0000

Data Index: 377922 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4610. Min Act: -0.0000

Data Index: 325817 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4059. Min Act: -0.0000

Data Index: 89633 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1309760 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1206316 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4185. Min Act: -0.0000

Data Index: 126893 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4184. Min Act: -0.0000

Data Index: 679949 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4263. Min Act: -0.0000

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4197. Min Act: -0.0000

Data Index: 86064 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1168764 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3603. Min Act: -0.0000

Data Index: 167149 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1146174 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1014737 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1231901 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3616. Min Act: -0.0000

Data Index: 450368 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3705. Min Act: -0.0000

Data Index: 507387 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3565. Min Act: -0.0000

Data Index: 358562 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3563. Min Act: -0.0000

Data Index: 613003 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3609. Min Act: -0.0000

Data Index: 598729 (C4 (Web Text))

Max Activating Token Index: 662