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

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

Neuron 69 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1655569 (Python Code)

Max Activating Token Index: 469

Text #1

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1125905 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7130. Min Act: -0.0000

Data Index: 853691 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1498956 (Python Code)

Max Activating Token Index: 963

Text #4

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6164. Min Act: -0.0000

Data Index: 363963 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5702. Min Act: -0.0000

Data Index: 342087 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6652. Min Act: -0.0000

Data Index: 954372 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5406. Min Act: -0.0000

Data Index: 825108 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1605861 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1360668 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4932. Min Act: -0.0000

Data Index: 870851 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1395879 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5092. Min Act: -0.0000

Data Index: 927158 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1395799 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5173. Min Act: -0.0000

Data Index: 266465 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5319. Min Act: -0.0000

Data Index: 981264 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4962. Min Act: -0.0000

Data Index: 69525 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1147098 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1639001 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4887. Min Act: -0.0000

Data Index: 180436 (C4 (Web Text))

Max Activating Token Index: 665