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

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

Neuron 3655 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: 1.2991. Min Range: -1.2991

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1112187 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.2388. Min Act: -0.0000

Data Index: 709756 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.2991. Min Act: -0.0000

Data Index: 146033 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.1855. Min Act: -0.0000

Data Index: 640965 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.0707. Min Act: -0.0000

Data Index: 340282 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9916. Min Act: -0.0000

Data Index: 222437 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1172237 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.0954. Min Act: -0.0000

Data Index: 389057 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1274324 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.2991. Min Range: -1.2991

Max Act: 1.0138. Min Act: -0.0000

Data Index: 471612 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1183301 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9669. Min Act: -0.0000

Data Index: 398434 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1325725 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1240164 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9234. Min Act: -0.0000

Data Index: 949035 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9246. Min Act: -0.0000

Data Index: 823084 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9554. Min Act: -0.0000

Data Index: 670011 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9387. Min Act: -0.0000

Data Index: 744653 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.8773. Min Act: -0.0000

Data Index: 477730 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.2991. Min Range: -1.2991

Max Act: 0.9012. Min Act: -0.0000

Data Index: 605868 (C4 (Web Text))

Max Activating Token Index: 582