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

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

Neuron 996 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1550060 (Python Code)

Max Activating Token Index: 537

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1499362 (Python Code)

Max Activating Token Index: 425

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1645490 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1369435 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1376790 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1529565 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1435391 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1447091 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1648957 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1443946 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1476589 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1392436 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1410601 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1398784 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1388764 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1569012 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1402342 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1609009 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1404209 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1436424 (Python Code)

Max Activating Token Index: 946