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

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

Neuron 4177 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: 0.2748. Min Range: -0.2748

Max Act: 0.2748. Min Act: -0.0000

Data Index: 662263 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2626. Min Act: -0.0000

Data Index: 189720 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2434. Min Act: -0.0000

Data Index: 612253 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2334. Min Act: -0.0000

Data Index: 994715 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2227. Min Act: -0.0000

Data Index: 857544 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2051. Min Act: -0.0000

Data Index: 439760 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1074474 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2038. Min Act: -0.0000

Data Index: 254561 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.2065. Min Act: -0.0000

Data Index: 3685 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1983. Min Act: -0.0000

Data Index: 180431 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1981. Min Act: -0.0000

Data Index: 805376 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1945. Min Act: -0.0000

Data Index: 618246 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1308538 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1198808 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1908. Min Act: -0.0000

Data Index: 759870 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1201255 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1839. Min Act: -0.0000

Data Index: 560590 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1959. Min Act: -0.0000

Data Index: 555350 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1824. Min Act: -0.0000

Data Index: 162425 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2748. Min Range: -0.2748

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1215176 (C4 (Web Text))

Max Activating Token Index: 876