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

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

Neuron 1013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2203. Min Act: -0.0002

Data Index: 125175 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2065. Min Act: -0.0002

Data Index: 735469 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.2060. Min Act: -0.0002

Data Index: 817471 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1904. Min Act: -0.0002

Data Index: 1148587 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1898. Min Act: -0.0002

Data Index: 975562 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1876. Min Act: -0.0002

Data Index: 1271274 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1934. Min Act: -0.0002

Data Index: 117747 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1870. Min Act: -0.0002

Data Index: 772449 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1836. Min Act: -0.0002

Data Index: 243562 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1771. Min Act: -0.0002

Data Index: 1630199 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1835. Min Act: -0.0002

Data Index: 281351 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1757. Min Act: -0.0002

Data Index: 678684 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1725. Min Act: -0.0002

Data Index: 299582 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1747. Min Act: -0.0002

Data Index: 718423 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1744. Min Act: -0.0002

Data Index: 732386 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1725. Min Act: -0.0002

Data Index: 1565656 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1742. Min Act: -0.0002

Data Index: 233154 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1735. Min Act: -0.0002

Data Index: 771076 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1278487 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.2203. Min Range: -0.2203

Max Act: 0.1777. Min Act: -0.0002

Data Index: 1359790 (C4 (Web Text))

Max Activating Token Index: 41