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

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

Neuron 2864 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1069. Min Range: -2.1069

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1650040 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1545670 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.5007. Min Act: -0.0000

Data Index: 1514184 (Python Code)

Max Activating Token Index: 1008

Text #3

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1654887 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1418174 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1641644 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1418677 (Python Code)

Max Activating Token Index: 820

Text #7

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1546561 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.0588. Min Act: -0.0000

Data Index: 1483407 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 2.1069. Min Range: -2.1069

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1397009 (Python Code)

Max Activating Token Index: 731

Text #10

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1547844 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1446634 (Python Code)

Max Activating Token Index: 979

Text #12

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1437733 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1607090 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1497224 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1448566 (Python Code)

Max Activating Token Index: 580

Text #16

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1412889 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1444059 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1616893 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 2.1069. Min Range: -2.1069

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1397441 (Python Code)

Max Activating Token Index: 666