Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1468667 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8239. Min Act: -0.0001

Data Index: 1594618 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8633. Min Act: -0.0002

Data Index: 1576047 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.9652. Min Act: -0.0001

Data Index: 1489503 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1634463 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8282. Min Act: -0.0002

Data Index: 1480956 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1478207 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8377. Min Act: -0.0001

Data Index: 1649992 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.9080. Min Act: -0.0001

Data Index: 1538216 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7900. Min Act: -0.0001

Data Index: 1483216 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8114. Min Act: -0.0001

Data Index: 1436069 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1377170 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1395930 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7938. Min Act: -0.0001

Data Index: 1558302 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.8185. Min Act: -0.0001

Data Index: 1382664 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1530603 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1510744 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7787. Min Act: -0.0001

Data Index: 1485013 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1607520 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 0.9652. Min Range: -0.9652

Max Act: 0.7461. Min Act: -0.0001

Data Index: 1654597 (Python Code)

Max Activating Token Index: 91