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

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

Neuron 76 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1535021 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1493581 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 1.0076. Min Range: -1.0076

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1594707 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1543918 (Python Code)

Max Activating Token Index: 390

Text #4

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1428971 (Python Code)

Max Activating Token Index: 779

Text #5

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1560695 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1377766 (Python Code)

Max Activating Token Index: 132

Text #7

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1387086 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1494422 (Python Code)

Max Activating Token Index: 389

Text #9

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.8073. Min Act: -0.0001

Data Index: 1384410 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1490583 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1472727 (Python Code)

Max Activating Token Index: 731

Text #12

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1374726 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1605526 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1524929 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1558514 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1439430 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1545686 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1403743 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 1.0076. Min Range: -1.0076

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1470420 (Python Code)

Max Activating Token Index: 434