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

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

Neuron 4992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.5873. Min Act: -0.0000

Data Index: 204696 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4819. Min Act: -0.0000

Data Index: 752054 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4752. Min Act: -0.0000

Data Index: 868827 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4450. Min Act: -0.0000

Data Index: 210543 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1154944 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1319144 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1175410 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4186. Min Act: -0.0000

Data Index: 1076965 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4248. Min Act: -0.0000

Data Index: 914999 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1202068 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.4007. Min Act: -0.0000

Data Index: 966103 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3963. Min Act: -0.0000

Data Index: 910602 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3933. Min Act: -0.0000

Data Index: 66178 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3834. Min Act: -0.0000

Data Index: 203196 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3915. Min Act: -0.0000

Data Index: 110382 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3755. Min Act: -0.0000

Data Index: 434529 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3718. Min Act: -0.0000

Data Index: 422980 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3648. Min Act: -0.0000

Data Index: 982436 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1239789 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.5873. Min Range: -0.5873

Max Act: 0.3569. Min Act: -0.0000

Data Index: 220 (C4 (Web Text))

Max Activating Token Index: 470