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

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

Neuron 4034 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.3561. Min Act: -0.0001

Data Index: 1504341 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0642. Min Act: -0.0001

Data Index: 1517975 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.1306. Min Act: -0.0001

Data Index: 1597572 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0048. Min Act: -0.0001

Data Index: 1568723 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.1107. Min Act: -0.0001

Data Index: 1519754 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.1172. Min Act: -0.0001

Data Index: 1418002 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0810. Min Act: -0.0001

Data Index: 1583183 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0780. Min Act: -0.0001

Data Index: 1437899 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1443973 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1642194 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9933. Min Act: -0.0001

Data Index: 1422820 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0489. Min Act: -0.0001

Data Index: 1461779 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0858. Min Act: -0.0001

Data Index: 1440741 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0911. Min Act: -0.0001

Data Index: 1621849 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0987. Min Act: -0.0001

Data Index: 1368311 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1376101 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9938. Min Act: -0.0001

Data Index: 1376714 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1536603 (Python Code)

Max Activating Token Index: 242

Text #18

Max Range: 1.3561. Min Range: -1.3561

Max Act: 1.1202. Min Act: -0.0001

Data Index: 1561770 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 1.3561. Min Range: -1.3561

Max Act: 0.9847. Min Act: -0.0001

Data Index: 1491560 (Python Code)

Max Activating Token Index: 642