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

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

Neuron 4592 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0000

Data Index: 1053421 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1279346 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0000

Data Index: 322323 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0000

Data Index: 22016 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0000

Data Index: 814393 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0000

Data Index: 928618 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0063. Min Act: -0.0000

Data Index: 1001745 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0000

Data Index: 177760 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0064. Min Act: -0.0000

Data Index: 1264646 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0000

Data Index: 544634 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0001

Data Index: 778151 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0000

Data Index: 704432 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0000

Data Index: 184489 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0000

Data Index: 1188490 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0057. Min Act: -0.0000

Data Index: 126607 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0000

Data Index: 863920 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0056. Min Act: -0.0001

Data Index: 714899 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0049. Min Act: -0.0000

Data Index: 896685 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0000

Data Index: 176462 (C4 (Web Text))

Max Activating Token Index: 459