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

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

Neuron 4646 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5112. Min Range: -1.5112

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1542585 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8733. Min Act: -0.0000

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8640. Min Act: -0.0000

Data Index: 667417 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1464073 (Python Code)

Max Activating Token Index: 734

Text #4

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.7082. Min Act: -0.0000

Data Index: 150013 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1230280 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.6894. Min Act: -0.0000

Data Index: 243661 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1557390 (Python Code)

Max Activating Token Index: 445

Text #8

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1507620 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5472. Min Act: -0.0000

Data Index: 26850 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1400588 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5605. Min Act: -0.0000

Data Index: 689217 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5972. Min Act: -0.0000

Data Index: 612298 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5645. Min Act: -0.0000

Data Index: 816351 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.4829. Min Act: -0.0000

Data Index: 848783 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1062413 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1377299 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1607572 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.4750. Min Act: -0.0000

Data Index: 528965 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.5112. Min Range: -1.5112

Max Act: 0.5822. Min Act: -0.0000

Data Index: 124397 (C4 (Web Text))

Max Activating Token Index: 248