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

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

Neuron 6061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1554257 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1350547 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1512865 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1137. Min Act: -0.0001

Data Index: 192087 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1597728 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0998. Min Act: -0.0001

Data Index: 618639 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1655595 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1336860 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0918. Min Act: -0.0000

Data Index: 255421 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1589608 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0939. Min Act: -0.0001

Data Index: 886714 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0944. Min Act: -0.0000

Data Index: 99697 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1061353 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1574438 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1565122 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1569347 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1487230 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1376821 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1590164 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1539340 (Python Code)

Max Activating Token Index: 66