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

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

Neuron 4099 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: 2.1267. Min Range: -2.1267

Max Act: 2.1267. Min Act: -0.0000

Data Index: 1180209 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.9964. Min Act: -0.0000

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 2.1267. Min Range: -2.1267

Max Act: 2.0455. Min Act: -0.0000

Data Index: 1398213 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1499991 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1398170 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1612622 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1387968 (Python Code)

Max Activating Token Index: 889

Text #7

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6035. Min Act: -0.0000

Data Index: 1638863 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6094. Min Act: -0.0000

Data Index: 1398535 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.7635. Min Act: -0.0000

Data Index: 1516586 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.5785. Min Act: -0.0000

Data Index: 1225442 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1516009 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6362. Min Act: -0.0000

Data Index: 890222 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1463680 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1165794 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1573211 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1470562 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1492010 (Python Code)

Max Activating Token Index: 1013

Text #18

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.5360. Min Act: -0.0000

Data Index: 1632130 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 2.1267. Min Range: -2.1267

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1378119 (Python Code)

Max Activating Token Index: 941