Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.4815. Min Act: -0.0000

Data Index: 626743 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2740. Min Act: -0.0001

Data Index: 484458 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2092. Min Act: -0.0001

Data Index: 966811 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1948. Min Act: -0.0001

Data Index: 41755 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2089. Min Act: -0.0001

Data Index: 276981 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2121. Min Act: -0.0001

Data Index: 853661 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1980. Min Act: -0.0001

Data Index: 155693 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1326690 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1041544 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1865. Min Act: -0.0001

Data Index: 671281 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1806. Min Act: -0.0001

Data Index: 98271 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1793. Min Act: -0.0001

Data Index: 195810 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1359116 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1765. Min Act: -0.0001

Data Index: 488813 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1708. Min Act: -0.0001

Data Index: 818350 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1800. Min Act: -0.0001

Data Index: 292586 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1921. Min Act: -0.0001

Data Index: 94917 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1797. Min Act: -0.0001

Data Index: 977757 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1711. Min Act: -0.0001

Data Index: 315905 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1351902 (C4 (Web Text))

Max Activating Token Index: 945