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

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

Neuron 6025 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1364. Min Act: -0.0001

Data Index: 597467 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1401. Min Act: -0.0002

Data Index: 269194 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1540035 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1063. Min Act: -0.0001

Data Index: 245250 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1570825 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1049. Min Act: -0.0001

Data Index: 684739 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1095. Min Act: -0.0001

Data Index: 811658 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1087588 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1412492 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0953. Min Act: -0.0001

Data Index: 766833 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0942. Min Act: -0.0001

Data Index: 252801 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0927. Min Act: -0.0001

Data Index: 613816 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0893. Min Act: -0.0001

Data Index: 613436 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0907. Min Act: -0.0001

Data Index: 12707 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0938. Min Act: -0.0001

Data Index: 953994 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1403024 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1277208 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1494303 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1237417 (C4 (Web Text))

Max Activating Token Index: 288