Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 573 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0002

Data Index: 308221 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4345. Min Act: -0.0002

Data Index: 213082 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4404. Min Act: -0.0002

Data Index: 1117211 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4375. Min Act: -0.0002

Data Index: 899881 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4228. Min Act: -0.0002

Data Index: 1215470 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4222. Min Act: -0.0003

Data Index: 160194 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4098. Min Act: -0.0002

Data Index: 354224 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4044. Min Act: -0.0002

Data Index: 1290470 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4030. Min Act: -0.0002

Data Index: 1289134 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4111. Min Act: -0.0002

Data Index: 196732 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4131. Min Act: -0.0002

Data Index: 979294 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4061. Min Act: -0.0002

Data Index: 529326 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3949. Min Act: -0.0003

Data Index: 414131 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3943. Min Act: -0.0002

Data Index: 688379 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3984. Min Act: -0.0002

Data Index: 1240378 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3946. Min Act: -0.0003

Data Index: 166618 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4016. Min Act: -0.0002

Data Index: 158675 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3906. Min Act: -0.0002

Data Index: 27326 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4023. Min Act: -0.0003

Data Index: 164368 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3979. Min Act: -0.0002

Data Index: 1064446 (C4 (Web Text))

Max Activating Token Index: 789