Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0653. Min Act: -0.0003

Data Index: 605252 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0657. Min Act: -0.0003

Data Index: 775559 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0623. Min Act: -0.0003

Data Index: 522691 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0605. Min Act: -0.0003

Data Index: 361028 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0599. Min Act: -0.0003

Data Index: 433828 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1155083 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0619. Min Act: -0.0003

Data Index: 977757 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1031598 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0567. Min Act: -0.0003

Data Index: 936877 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1016019 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0569. Min Act: -0.0003

Data Index: 936880 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1312447 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0546. Min Act: -0.0003

Data Index: 640121 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0525. Min Act: -0.0003

Data Index: 558577 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0528. Min Act: -0.0003

Data Index: 680578 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0526. Min Act: -0.0003

Data Index: 30835 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1066783 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0539. Min Act: -0.0003

Data Index: 925357 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1301941 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0657. Min Range: -0.0657

Max Act: 0.0514. Min Act: -0.0003

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 496