Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 176 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.1830. Min Act: -0.0000

Data Index: 1391429 (Python Code)

Max Activating Token Index: 161

Text #1

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0954. Min Act: -0.0000

Data Index: 1414978 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0646. Min Act: -0.0000

Data Index: 1531142 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0290. Min Act: -0.0000

Data Index: 1533918 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.2007. Min Act: -0.0000

Data Index: 1533869 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.2058. Min Act: -0.0000

Data Index: 1458245 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.6272. Min Act: -0.0001

Data Index: 1432860 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.1079. Min Act: -0.0001

Data Index: 1528756 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0693. Min Act: -0.0000

Data Index: 1552404 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.9119. Min Act: -0.0000

Data Index: 1608893 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.7523. Min Act: -0.0000

Data Index: 1491886 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0511. Min Act: -0.0001

Data Index: 1383418 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0168. Min Act: -0.0001

Data Index: 1497051 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.1565. Min Act: -0.0000

Data Index: 1532296 (Python Code)

Max Activating Token Index: 758

Text #14

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.8661. Min Act: -0.0000

Data Index: 1637096 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.8110. Min Act: -0.0001

Data Index: 1520574 (Python Code)

Max Activating Token Index: 408

Text #16

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.8576. Min Act: -0.0001

Data Index: 1605739 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.6819. Min Act: -0.0000

Data Index: 1535070 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 4.2058. Min Range: -4.2058

Max Act: 4.0056. Min Act: -0.0001

Data Index: 1500196 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 4.2058. Min Range: -4.2058

Max Act: 3.8373. Min Act: -0.0001

Data Index: 1397852 (Python Code)

Max Activating Token Index: 301