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

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

Neuron 3472 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: 1.1480. Min Range: -1.1480

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1517655 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1228. Min Act: -0.0000

Data Index: 1576621 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1569720 (Python Code)

Max Activating Token Index: 238

Text #3

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1416122 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1394408 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1570867 (Python Code)

Max Activating Token Index: 289

Text #6

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1625822 (Python Code)

Max Activating Token Index: 287

Text #7

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1422588 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9973. Min Act: -0.0000

Data Index: 1571871 (Python Code)

Max Activating Token Index: 379

Text #9

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1554341 (Python Code)

Max Activating Token Index: 681

Text #10

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1599585 (Python Code)

Max Activating Token Index: 752

Text #11

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1387001 (Python Code)

Max Activating Token Index: 896

Text #12

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1367618 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1625130 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1647018 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1635141 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 1.1480. Min Range: -1.1480

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1498719 (Python Code)

Max Activating Token Index: 927

Text #17

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1485020 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1508976 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.1480. Min Range: -1.1480

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1532928 (Python Code)

Max Activating Token Index: 695