Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 879 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3309. Min Act: -0.0002

Data Index: 1365514 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3105. Min Act: 0.0003

Data Index: 1560080 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.3071. Min Act: 0.0000

Data Index: 1394888 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2942. Min Act: -0.0002

Data Index: 1360588 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2734. Min Act: -0.0001

Data Index: 1581501 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2782. Min Act: 0.0000

Data Index: 1496727 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1549761 (Python Code)

Max Activating Token Index: 618

Text #7

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2770. Min Act: 0.0001

Data Index: 1461987 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1628254 (Python Code)

Max Activating Token Index: 889

Text #9

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1379408 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1632917 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1617853 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1626332 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1489343 (Python Code)

Max Activating Token Index: 542

Text #14

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2835. Min Act: 0.0002

Data Index: 1436848 (Python Code)

Max Activating Token Index: 696

Text #15

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2530. Min Act: -0.0002

Data Index: 1638400 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1412902 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2615. Min Act: 0.0001

Data Index: 1440937 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1624539 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 0.3309. Min Range: -0.3309

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1568505 (Python Code)

Max Activating Token Index: 755