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

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

Neuron 1255 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.8381. Min Act: -0.0001

Data Index: 1302926 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.7362. Min Act: -0.0000

Data Index: 722779 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.7217. Min Act: -0.0001

Data Index: 1092651 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.8934. Min Act: -0.0000

Data Index: 925501 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.7579. Min Act: -0.0001

Data Index: 1289979 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.6261. Min Act: -0.0001

Data Index: 233724 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.6185. Min Act: -0.0001

Data Index: 235577 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.3631. Min Act: -0.0001

Data Index: 610874 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5067. Min Act: -0.0001

Data Index: 1318741 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.4169. Min Act: -0.0001

Data Index: 107087 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5191. Min Act: -0.0000

Data Index: 654692 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.4998. Min Act: -0.0001

Data Index: 116121 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5388. Min Act: -0.0001

Data Index: 1285566 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5918. Min Act: -0.0001

Data Index: 358839 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.4208. Min Act: -0.0001

Data Index: 183124 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5388. Min Act: -0.0001

Data Index: 1168501 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1113097 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.5014. Min Act: -0.0000

Data Index: 822340 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.3773. Min Act: -0.0001

Data Index: 598807 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 1.8934. Min Range: -1.8934

Max Act: 1.3816. Min Act: -0.0001

Data Index: 211953 (C4 (Web Text))

Max Activating Token Index: 828