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

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

Neuron 3619 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1183183 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0660. Min Act: -0.0002

Data Index: 532796 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0604. Min Act: -0.0002

Data Index: 680815 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0565. Min Act: -0.0002

Data Index: 379650 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1238341 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0514. Min Act: -0.0002

Data Index: 890215 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0540. Min Act: -0.0002

Data Index: 152252 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0500. Min Act: -0.0002

Data Index: 674324 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0463. Min Act: -0.0002

Data Index: 957497 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1062669 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0475. Min Act: -0.0002

Data Index: 73580 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1306460 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0493. Min Act: -0.0002

Data Index: 995158 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0497. Min Act: -0.0002

Data Index: 840017 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0475. Min Act: -0.0002

Data Index: 61033 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1546531 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0470. Min Act: -0.0002

Data Index: 400467 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0442. Min Act: -0.0002

Data Index: 902862 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1118582 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1130073 (C4 (Web Text))

Max Activating Token Index: 666