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

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

Neuron 419 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.9327. Min Act: -0.0000

Data Index: 84441 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.8286. Min Act: -0.0000

Data Index: 554812 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1328334 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.6427. Min Act: -0.0000

Data Index: 652576 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5330. Min Act: -0.0000

Data Index: 982878 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5913. Min Act: -0.0000

Data Index: 620038 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1646105 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1646041 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.6758. Min Act: -0.0000

Data Index: 1305476 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5727. Min Act: -0.0000

Data Index: 283357 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1283682 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5547. Min Act: -0.0000

Data Index: 451956 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5284. Min Act: -0.0000

Data Index: 663230 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.4289. Min Act: -0.0000

Data Index: 984158 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1480286 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.6014. Min Act: -0.0000

Data Index: 519069 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1636707 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.4068. Min Act: -0.0000

Data Index: 545411 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.3971. Min Act: -0.0000

Data Index: 667198 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 1.9327. Min Range: -1.9327

Max Act: 1.3650. Min Act: -0.0000

Data Index: 938572 (C4 (Web Text))

Max Activating Token Index: 847