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

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

Neuron 1789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6981. Min Act: -0.0000

Data Index: 592927 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6086. Min Act: -0.0000

Data Index: 808177 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6367. Min Act: -0.0000

Data Index: 372174 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6307. Min Act: -0.0000

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6050. Min Act: -0.0000

Data Index: 43734 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6210. Min Act: -0.0000

Data Index: 670231 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5930. Min Act: -0.0000

Data Index: 234053 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.6057. Min Act: -0.0000

Data Index: 391131 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5976. Min Act: -0.0000

Data Index: 269032 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5693. Min Act: -0.0000

Data Index: 420449 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1256063 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5631. Min Act: -0.0000

Data Index: 799461 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5667. Min Act: -0.0000

Data Index: 184328 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5268. Min Act: -0.0000

Data Index: 308962 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5255. Min Act: -0.0000

Data Index: 586861 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1195027 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1350763 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.4996. Min Act: -0.0000

Data Index: 716741 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5038. Min Act: -0.0000

Data Index: 11494 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.6981. Min Range: -0.6981

Max Act: 0.5014. Min Act: -0.0000

Data Index: 57588 (C4 (Web Text))

Max Activating Token Index: 960