Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4167 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.8914. Min Act: -0.0000

Data Index: 1085494 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.5955. Min Act: -0.0000

Data Index: 881510 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.4211. Min Act: -0.0000

Data Index: 1605699 (Python Code)

Max Activating Token Index: 857

Text #3

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.5291. Min Act: -0.0000

Data Index: 1561543 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.3149. Min Act: -0.0000

Data Index: 1379407 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.2879. Min Act: -0.0000

Data Index: 1168537 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.4643. Min Act: -0.0000

Data Index: 1651349 (Python Code)

Max Activating Token Index: 938

Text #7

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1582074 (Python Code)

Max Activating Token Index: 319

Text #8

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.1890. Min Act: -0.0000

Data Index: 318200 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.3069. Min Act: -0.0000

Data Index: 1571485 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.2640. Min Act: -0.0000

Data Index: 1405735 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.2556. Min Act: -0.0000

Data Index: 1380410 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.3730. Min Act: -0.0000

Data Index: 780901 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.2497. Min Act: -0.0000

Data Index: 1265687 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1530158 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.0670. Min Act: -0.0000

Data Index: 391062 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.0503. Min Act: -0.0000

Data Index: 1615886 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.1537. Min Act: -0.0000

Data Index: 1234302 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 2.8914. Min Range: -2.8914

Max Act: 2.1134. Min Act: -0.0000

Data Index: 19534 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 2.8914. Min Range: -2.8914

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1500082 (Python Code)

Max Activating Token Index: 710