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

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

Neuron 2556 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.8876. Min Act: -0.0000

Data Index: 1630681 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.9007. Min Act: -0.0000

Data Index: 1604248 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.5433. Min Act: 0.0000

Data Index: 1656384 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.3501. Min Act: -0.0000

Data Index: 1594922 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 2.9007. Min Range: -2.9007

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1636293 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9269. Min Act: -0.0000

Data Index: 1601998 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.9114. Min Act: 0.0000

Data Index: 1438696 (Python Code)

Max Activating Token Index: 332

Text #7

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8177. Min Act: -0.0000

Data Index: 1130848 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1443032 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1464958 (Python Code)

Max Activating Token Index: 407

Text #10

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1367885 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7015. Min Act: -0.0000

Data Index: 210053 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7600. Min Act: -0.0000

Data Index: 440746 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1648699 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1480464 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1504507 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6207. Min Act: -0.0000

Data Index: 1557522 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1630916 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.4525. Min Act: -0.0000

Data Index: 663109 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 2.9007. Min Range: -2.9007

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1393411 (Python Code)

Max Activating Token Index: 313