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

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

Neuron 1974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1431997 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1433699 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1638993 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1415622 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1500079 (Python Code)

Max Activating Token Index: 60

Text #5

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1458600 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1502224 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1545683 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1381708 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1523295 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1389337 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1482764 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1607593 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1651135 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1483928 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1471291 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1393851 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1654571 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1575118 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.4650. Min Range: -0.4650

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1611704 (Python Code)

Max Activating Token Index: 704