Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3245 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1573429 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1188040 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1605990 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1544472 (Python Code)

Max Activating Token Index: 459

Text #4

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.3877. Min Act: -0.0000

Data Index: 489379 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.3196. Min Act: -0.0000

Data Index: 517394 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.2322. Min Act: -0.0000

Data Index: 324237 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1930. Min Act: -0.0000

Data Index: 872306 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1548337 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1350. Min Act: -0.0000

Data Index: 33205 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1974. Min Act: -0.0000

Data Index: 241836 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1394028 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1551842 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.2205. Min Act: -0.0000

Data Index: 754288 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1794. Min Act: -0.0000

Data Index: 1559384 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.0863. Min Act: -0.0000

Data Index: 54248 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1599669 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1897. Min Act: -0.0000

Data Index: 514750 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1453818 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 1.4608. Min Range: -1.4608

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1608362 (Python Code)

Max Activating Token Index: 402