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

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

Neuron 5570 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0309. Min Range: -2.0309

Max Act: 2.0309. Min Act: -0.0000

Data Index: 1579293 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8539. Min Act: -0.0000

Data Index: 1418648 (Python Code)

Max Activating Token Index: 852

Text #2

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1512232 (Python Code)

Max Activating Token Index: 665

Text #3

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.6065. Min Act: -0.0000

Data Index: 1630450 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.8025. Min Act: -0.0000

Data Index: 1569595 (Python Code)

Max Activating Token Index: 995

Text #5

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.5828. Min Act: 0.0000

Data Index: 1539345 (Python Code)

Max Activating Token Index: 911

Text #6

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1405617 (Python Code)

Max Activating Token Index: 553

Text #7

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.6613. Min Act: 0.0000

Data Index: 1555873 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.5297. Min Act: 0.0000

Data Index: 1391934 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4795. Min Act: -0.0000

Data Index: 1550545 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1364600 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4560. Min Act: -0.0000

Data Index: 1404976 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4163. Min Act: -0.0000

Data Index: 1573024 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1468062 (Python Code)

Max Activating Token Index: 467

Text #14

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1542947 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.4068. Min Act: 0.0001

Data Index: 1536780 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1529891 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.3958. Min Act: -0.0000

Data Index: 1383211 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1623956 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 2.0309. Min Range: -2.0309

Max Act: 1.3385. Min Act: 0.0000

Data Index: 1432305 (Python Code)

Max Activating Token Index: 62