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

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

Neuron 3567 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1464491 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 2.0523. Min Range: -2.0523

Max Act: 2.0523. Min Act: -0.0000

Data Index: 1533070 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.9177. Min Act: -0.0000

Data Index: 1586264 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1410444 (Python Code)

Max Activating Token Index: 205

Text #4

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1582745 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1391792 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.7028. Min Act: -0.0000

Data Index: 1635074 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6900. Min Act: -0.0000

Data Index: 1512527 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.7632. Min Act: -0.0000

Data Index: 1609084 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6529. Min Act: -0.0000

Data Index: 1392129 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1635137 (Python Code)

Max Activating Token Index: 680

Text #11

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1371245 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1495616 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1563061 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5728. Min Act: -0.0000

Data Index: 1554953 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1401070 (Python Code)

Max Activating Token Index: 968

Text #16

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1362903 (Python Code)

Max Activating Token Index: 530

Text #17

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1488435 (Python Code)

Max Activating Token Index: 680

Text #18

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.6398. Min Act: -0.0000

Data Index: 1379944 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 2.0523. Min Range: -2.0523

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1494839 (Python Code)

Max Activating Token Index: 396