Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3989 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.7840. Min Act: -0.0001

Data Index: 1634419 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.4602. Min Act: -0.0001

Data Index: 1600364 (Python Code)

Max Activating Token Index: 74

Text #2

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.0104. Min Act: -0.0001

Data Index: 1365810 (Python Code)

Max Activating Token Index: 1020

Text #3

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.0735. Min Act: -0.0001

Data Index: 1653548 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.9411. Min Act: -0.0001

Data Index: 1612629 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.0195. Min Act: -0.0001

Data Index: 1570526 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.8492. Min Act: -0.0001

Data Index: 1462831 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.7966. Min Act: -0.0001

Data Index: 1528488 (Python Code)

Max Activating Token Index: 853

Text #8

Max Range: 3.7840. Min Range: -3.7840

Max Act: 3.0624. Min Act: -0.0001

Data Index: 1527127 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.8195. Min Act: -0.0001

Data Index: 1392006 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.8068. Min Act: -0.0001

Data Index: 1639100 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.5472. Min Act: -0.0001

Data Index: 1560119 (Python Code)

Max Activating Token Index: 194

Text #12

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.7970. Min Act: -0.0001

Data Index: 1622684 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.7571. Min Act: -0.0001

Data Index: 1633906 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.8875. Min Act: -0.0001

Data Index: 1632055 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.7587. Min Act: -0.0001

Data Index: 1369348 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.6023. Min Act: -0.0001

Data Index: 1382778 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.7072. Min Act: -0.0001

Data Index: 1376788 (Python Code)

Max Activating Token Index: 502

Text #18

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.8316. Min Act: -0.0001

Data Index: 1571125 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 3.7840. Min Range: -3.7840

Max Act: 2.6944. Min Act: -0.0001

Data Index: 1367522 (Python Code)

Max Activating Token Index: 226