Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1207 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1589339 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1415877 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1247. Min Act: -0.0003

Data Index: 1629791 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1452982 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1145. Min Act: -0.0003

Data Index: 1648901 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1140. Min Act: -0.0003

Data Index: 1361429 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1425769 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1653784 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1437845 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1437634 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1412877 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1091. Min Act: -0.0003

Data Index: 1603689 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1552226 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1377520 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1035. Min Act: -0.0004

Data Index: 1435200 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1464037 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1605039 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1464959 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1607617 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1554953 (Python Code)

Max Activating Token Index: 992