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

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

Neuron 2128 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.8499. Min Act: -0.0000

Data Index: 975922 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.4768. Min Act: -0.0000

Data Index: 578526 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.2898. Min Act: -0.0000

Data Index: 1082390 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.4528. Min Act: -0.0000

Data Index: 115053 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.1076. Min Act: -0.0000

Data Index: 705548 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.0955. Min Act: -0.0000

Data Index: 1066122 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.3356. Min Act: -0.0000

Data Index: 1038293 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.1431. Min Act: -0.0000

Data Index: 1188642 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.0049. Min Act: -0.0000

Data Index: 334000 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.8499. Min Range: -3.8499

Max Act: 3.0025. Min Act: -0.0000

Data Index: 602617 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.7873. Min Act: -0.0000

Data Index: 609664 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.9094. Min Act: -0.0000

Data Index: 943448 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.9074. Min Act: -0.0000

Data Index: 8015 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1023477 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.8192. Min Act: -0.0000

Data Index: 798010 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.6210. Min Act: -0.0000

Data Index: 1246593 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.8319. Min Act: -0.0000

Data Index: 207080 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.6963. Min Act: -0.0000

Data Index: 810942 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.7632. Min Act: -0.0000

Data Index: 705546 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 3.8499. Min Range: -3.8499

Max Act: 2.5858. Min Act: -0.0000

Data Index: 386880 (C4 (Web Text))

Max Activating Token Index: 817