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

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

Neuron 1220 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: 1.5037. Min Range: -1.5037

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1487515 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.3238. Min Act: -0.0000

Data Index: 56172 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1239371 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.4368. Min Act: -0.0000

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2656. Min Act: -0.0000

Data Index: 1256843 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2062. Min Act: -0.0000

Data Index: 1081577 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1879. Min Act: -0.0000

Data Index: 361615 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1206. Min Act: -0.0000

Data Index: 688543 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1617684 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1480387 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1730. Min Act: -0.0000

Data Index: 297528 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1392435 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1203770 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1342864 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1544029 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1510808 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1576652 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 1.5037. Min Range: -1.5037

Max Act: 1.0374. Min Act: -0.0000

Data Index: 224327 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 1.5037. Min Range: -1.5037

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1597698 (Python Code)

Max Activating Token Index: 483

Text #19

Max Range: 1.5037. Min Range: -1.5037

Max Act: 0.9084. Min Act: -0.0000

Data Index: 252038 (C4 (Web Text))

Max Activating Token Index: 378