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

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

Neuron 4053 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0000

Data Index: 3867 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7983. Min Act: -0.0000

Data Index: 784129 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1023455 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8172. Min Act: -0.0000

Data Index: 336333 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7702. Min Act: -0.0000

Data Index: 378371 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1212423 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7795. Min Act: -0.0000

Data Index: 728215 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7994. Min Act: -0.0000

Data Index: 410693 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7270. Min Act: -0.0000

Data Index: 532265 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7844. Min Act: -0.0000

Data Index: 950282 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7482. Min Act: -0.0000

Data Index: 836370 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1356998 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1240496 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1067868 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7350. Min Act: -0.0000

Data Index: 887742 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1075323 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7072. Min Act: -0.0000

Data Index: 523424 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.6645. Min Act: -0.0000

Data Index: 563797 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 212