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

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

Neuron 1374 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1468. Min Range: -5.1468

Max Act: 5.1468. Min Act: -0.0000

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.6191. Min Act: -0.0000

Data Index: 156282 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.5981. Min Act: -0.0001

Data Index: 391984 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.1863. Min Act: -0.0000

Data Index: 333496 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.4160. Min Act: -0.0000

Data Index: 497759 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.1642. Min Act: -0.0000

Data Index: 1455152 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.9724. Min Act: -0.0000

Data Index: 481455 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.7126. Min Act: -0.0001

Data Index: 892383 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.0936. Min Act: -0.0000

Data Index: 82779 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.7991. Min Act: -0.0001

Data Index: 1147235 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.7846. Min Act: -0.0000

Data Index: 1253854 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.9314. Min Act: -0.0000

Data Index: 1597921 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.7634. Min Act: -0.0000

Data Index: 1562086 (Python Code)

Max Activating Token Index: 249

Text #13

Max Range: 5.1468. Min Range: -5.1468

Max Act: 4.0477. Min Act: -0.0000

Data Index: 1542629 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.6198. Min Act: -0.0000

Data Index: 899633 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.4410. Min Act: -0.0000

Data Index: 1591431 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.5965. Min Act: -0.0000

Data Index: 1420537 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.5544. Min Act: -0.0001

Data Index: 270727 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.5338. Min Act: -0.0000

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.1468. Min Range: -5.1468

Max Act: 3.5046. Min Act: -0.0000

Data Index: 1614608 (Python Code)

Max Activating Token Index: 550