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

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

Neuron 2240 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.7368. Min Act: -0.0001

Data Index: 551219 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6847. Min Act: -0.0001

Data Index: 279072 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1118723 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6915. Min Act: -0.0001

Data Index: 451538 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.7017. Min Act: -0.0001

Data Index: 899143 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6555. Min Act: -0.0001

Data Index: 728105 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6670. Min Act: -0.0001

Data Index: 1306333 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6697. Min Act: -0.0000

Data Index: 171669 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1118437 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6110. Min Act: -0.0001

Data Index: 672721 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6538. Min Act: -0.0001

Data Index: 378114 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6123. Min Act: -0.0001

Data Index: 865900 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6056. Min Act: -0.0001

Data Index: 825509 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1557073 (Python Code)

Max Activating Token Index: 674

Text #14

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5967. Min Act: -0.0001

Data Index: 740934 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5978. Min Act: -0.0001

Data Index: 665441 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5977. Min Act: -0.0001

Data Index: 539495 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5778. Min Act: -0.0001

Data Index: 136170 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5928. Min Act: -0.0001

Data Index: 521642 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.7368. Min Range: -0.7368

Max Act: 0.5883. Min Act: -0.0001

Data Index: 584397 (C4 (Web Text))

Max Activating Token Index: 484