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

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

Neuron 3549 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6931. Min Act: -0.0000

Data Index: 69628 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6734. Min Act: -0.0000

Data Index: 412572 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1304152 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1452027 (Python Code)

Max Activating Token Index: 704

Text #4

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6020. Min Act: -0.0000

Data Index: 164450 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1608469 (Python Code)

Max Activating Token Index: 902

Text #6

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1428491 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1547720 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1471788 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1475425 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1361407 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5758. Min Act: -0.0000

Data Index: 54726 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6081. Min Act: -0.0000

Data Index: 902162 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1638914 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1626184 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1468771 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1509140 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1428649 (Python Code)

Max Activating Token Index: 543

Text #18

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6307. Min Act: -0.0000

Data Index: 954883 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1394994 (Python Code)

Max Activating Token Index: 695