Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1942 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0003

Data Index: 544690 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1446388 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1346273 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0003

Data Index: 817243 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0003

Data Index: 432092 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0003

Data Index: 480861 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0003

Data Index: 579187 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1398706 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0003

Data Index: 310918 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0003

Data Index: 500660 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1190369 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1529931 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 283329 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 38795 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1284174 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 391806 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 684969 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 851272 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0003

Data Index: 262470 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1058493 (C4 (Web Text))

Max Activating Token Index: 984