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

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

Neuron 1985 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1486. Min Act: -0.0001

Data Index: 201210 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1240. Min Act: -0.0001

Data Index: 203996 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1139. Min Act: -0.0001

Data Index: 566616 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1107. Min Act: -0.0001

Data Index: 309015 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1105. Min Act: -0.0001

Data Index: 396574 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1230035 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1099. Min Act: -0.0001

Data Index: 465599 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1014. Min Act: -0.0001

Data Index: 769988 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1066355 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0969. Min Act: -0.0001

Data Index: 819931 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1003. Min Act: -0.0001

Data Index: 596000 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0872. Min Act: -0.0001

Data Index: 910384 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0980. Min Act: -0.0001

Data Index: 1088899 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0914. Min Act: -0.0001

Data Index: 441002 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1301749 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0968. Min Act: -0.0001

Data Index: 64899 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0923. Min Act: -0.0001

Data Index: 291409 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0985. Min Act: -0.0001

Data Index: 154873 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0915. Min Act: -0.0001

Data Index: 715439 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.1486. Min Range: -0.1486

Max Act: 0.0893. Min Act: -0.0001

Data Index: 519776 (C4 (Web Text))

Max Activating Token Index: 694