Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4260 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0002

Data Index: 774722 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0718. Min Act: -0.0002

Data Index: 632410 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1297169 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1336204 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1643421 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1371082 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0598. Min Act: -0.0002

Data Index: 366030 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1412117 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1455858 (Python Code)

Max Activating Token Index: 754

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1576858 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0546. Min Act: -0.0002

Data Index: 308573 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1364894 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0603. Min Act: -0.0002

Data Index: 594231 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1025175 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1427616 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0576. Min Act: -0.0002

Data Index: 419400 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1558214 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1174687 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1415834 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1390114 (Python Code)

Max Activating Token Index: 187