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

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

Neuron 863 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1091126 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2103. Min Act: -0.0000

Data Index: 802646 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2089. Min Act: -0.0000

Data Index: 100490 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1127373 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2027. Min Act: -0.0000

Data Index: 126544 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1905. Min Act: -0.0001

Data Index: 322877 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1328981 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1858. Min Act: -0.0000

Data Index: 462629 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1849. Min Act: -0.0000

Data Index: 473108 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1053836 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1890. Min Act: -0.0000

Data Index: 642740 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1015517 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1729. Min Act: -0.0001

Data Index: 855823 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1721. Min Act: -0.0000

Data Index: 401010 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1746. Min Act: -0.0000

Data Index: 529239 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1742. Min Act: -0.0000

Data Index: 764926 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1682. Min Act: -0.0000

Data Index: 209817 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1017095 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1343789 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1520813 (Python Code)

Max Activating Token Index: 252