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

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

Neuron 1416 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1521765 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1558827 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1607238 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1499803 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1479343 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1574363 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1399262 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1612483 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1553784 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1464144 (Python Code)

Max Activating Token Index: 904

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1608771 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1441898 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1381939 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1651254 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1481858 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1425337 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1436816 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0998. Min Act: -0.0001

Data Index: 481907 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1465757 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0796. Min Act: -0.0001

Data Index: 511862 (C4 (Web Text))

Max Activating Token Index: 199