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

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

Neuron 1471 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: 1.1311. Min Range: -1.1311

Max Act: 1.1311. Min Act: -0.0001

Data Index: 1378940 (Python Code)

Max Activating Token Index: 298

Text #1

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.1081. Min Act: -0.0001

Data Index: 1582215 (Python Code)

Max Activating Token Index: 773

Text #2

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.1278. Min Act: -0.0001

Data Index: 1402728 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0629. Min Act: -0.0001

Data Index: 1407102 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1573138 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0415. Min Act: -0.0001

Data Index: 1375668 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0389. Min Act: -0.0001

Data Index: 1621280 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0699. Min Act: -0.0001

Data Index: 1492077 (Python Code)

Max Activating Token Index: 303

Text #8

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1623682 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0443. Min Act: -0.0001

Data Index: 1493767 (Python Code)

Max Activating Token Index: 292

Text #10

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1479087 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1580450 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1603844 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0281. Min Act: -0.0001

Data Index: 1591666 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1533158 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0248. Min Act: -0.0001

Data Index: 1618017 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0137. Min Act: -0.0001

Data Index: 1576959 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1422402 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 1.1311. Min Range: -1.1311

Max Act: 1.0028. Min Act: -0.0001

Data Index: 1468785 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 1.1311. Min Range: -1.1311

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1454977 (Python Code)

Max Activating Token Index: 864