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

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

Neuron 3763 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: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1637463 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1617475 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1530205 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1641118 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1471862 (Python Code)

Max Activating Token Index: 439

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1411390 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1536369 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1507404 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1504555 (Python Code)

Max Activating Token Index: 858

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1596159 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1654874 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0610. Min Act: -0.0002

Data Index: 176457 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1387840 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1456166 (Python Code)

Max Activating Token Index: 464

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1221989 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1517426 (Python Code)

Max Activating Token Index: 280

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1403927 (Python Code)

Max Activating Token Index: 363

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1320093 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1582764 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1493980 (Python Code)

Max Activating Token Index: 376