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

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

Neuron 3238 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3898. Min Act: -0.0000

Data Index: 776543 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.4031. Min Act: -0.0001

Data Index: 1270047 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3802. Min Act: -0.0000

Data Index: 641640 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.4152. Min Act: -0.0000

Data Index: 25384 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1318960 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3988. Min Act: -0.0000

Data Index: 149697 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3989. Min Act: -0.0000

Data Index: 297059 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3825. Min Act: -0.0000

Data Index: 924077 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1008210 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3802. Min Act: -0.0000

Data Index: 622855 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.4191. Min Act: -0.0000

Data Index: 942283 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3521. Min Act: -0.0000

Data Index: 529433 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1327257 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3750. Min Act: -0.0000

Data Index: 291452 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3876. Min Act: -0.0000

Data Index: 846116 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1268212 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3863. Min Act: -0.0000

Data Index: 678801 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1262590 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3840. Min Act: -0.0000

Data Index: 381916 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.4191. Min Range: -0.4191

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1212168 (C4 (Web Text))

Max Activating Token Index: 638