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

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

Neuron 450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.7678. Min Act: -0.0000

Data Index: 732158 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.7571. Min Act: -0.0000

Data Index: 658346 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.6199. Min Act: -0.0000

Data Index: 724882 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.6057. Min Act: -0.0000

Data Index: 151130 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4963. Min Act: -0.0000

Data Index: 917802 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.6565. Min Act: -0.0000

Data Index: 617921 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1060776 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1208511 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5278. Min Act: -0.0000

Data Index: 173428 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5717. Min Act: -0.0000

Data Index: 641780 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5183. Min Act: -0.0000

Data Index: 143794 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1578674 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1067551 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4740. Min Act: -0.0000

Data Index: 214448 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5254. Min Act: -0.0000

Data Index: 7793 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1302894 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1437353 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5818. Min Act: -0.0000

Data Index: 152202 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1625651 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.7678. Min Range: -0.7678

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1656106 (Python Code)

Max Activating Token Index: 211