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

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

Neuron 3043 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: 0.1804. Min Range: -0.1804

Max Act: 0.1804. Min Act: -0.0002

Data Index: 765107 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1764. Min Act: -0.0002

Data Index: 10437 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1732. Min Act: -0.0003

Data Index: 250464 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1634. Min Act: -0.0003

Data Index: 982254 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1636. Min Act: -0.0002

Data Index: 391707 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1010352 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1624. Min Act: -0.0003

Data Index: 239874 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1629. Min Act: -0.0002

Data Index: 168088 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1522. Min Act: -0.0002

Data Index: 547409 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1588. Min Act: -0.0002

Data Index: 981076 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1539. Min Act: -0.0002

Data Index: 1320266 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1534. Min Act: -0.0002

Data Index: 710006 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1524. Min Act: -0.0002

Data Index: 967771 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1505. Min Act: -0.0002

Data Index: 638931 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1521. Min Act: -0.0002

Data Index: 190837 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1491. Min Act: -0.0002

Data Index: 485651 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1487. Min Act: -0.0003

Data Index: 150890 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1493. Min Act: -0.0002

Data Index: 208032 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1481. Min Act: -0.0002

Data Index: 367271 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.1804. Min Range: -0.1804

Max Act: 0.1508. Min Act: -0.0002

Data Index: 790180 (C4 (Web Text))

Max Activating Token Index: 933