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

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

Neuron 3637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1543549 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1428261 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1377430 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1400612 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1364080 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1362766 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1637399 (Python Code)

Max Activating Token Index: 270

Text #7

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1452748 (Python Code)

Max Activating Token Index: 698

Text #8

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1386893 (Python Code)

Max Activating Token Index: 818

Text #9

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1415341 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1391686 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4064. Min Act: -0.0000

Data Index: 1517596 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1572511 (Python Code)

Max Activating Token Index: 479

Text #13

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1537633 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1539133 (Python Code)

Max Activating Token Index: 914

Text #15

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1502193 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1459181 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1626950 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1567510 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 1.7516. Min Range: -1.7516

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1606170 (Python Code)

Max Activating Token Index: 370