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

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

Neuron 3017 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2139. Min Act: -0.0003

Data Index: 133685 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1869. Min Act: -0.0003

Data Index: 1353372 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1867. Min Act: -0.0003

Data Index: 758883 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1757. Min Act: -0.0002

Data Index: 827736 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1748. Min Act: -0.0002

Data Index: 652066 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1706. Min Act: -0.0002

Data Index: 425828 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1683. Min Act: -0.0002

Data Index: 854656 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1663. Min Act: -0.0003

Data Index: 801867 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1655. Min Act: -0.0003

Data Index: 390310 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1651. Min Act: -0.0002

Data Index: 1164658 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1649. Min Act: -0.0003

Data Index: 1354614 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1632. Min Act: -0.0002

Data Index: 874494 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1622. Min Act: -0.0003

Data Index: 305302 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1601. Min Act: -0.0003

Data Index: 1003367 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1548. Min Act: -0.0003

Data Index: 510114 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1572. Min Act: -0.0002

Data Index: 47496 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1574. Min Act: -0.0003

Data Index: 161933 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1543. Min Act: -0.0003

Data Index: 1100151 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1540. Min Act: -0.0003

Data Index: 1086134 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1517. Min Act: -0.0003

Data Index: 862621 (C4 (Web Text))

Max Activating Token Index: 166