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

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

Neuron 1529 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.1142. Min Act: -0.0002

Data Index: 1562770 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1523667 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.1142. Min Range: -1.1142

Max Act: 1.0113. Min Act: -0.0002

Data Index: 1474659 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9968. Min Act: -0.0002

Data Index: 1629609 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9997. Min Act: -0.0002

Data Index: 1455469 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9728. Min Act: -0.0002

Data Index: 1418389 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9611. Min Act: -0.0002

Data Index: 1366565 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9327. Min Act: -0.0002

Data Index: 1487167 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9477. Min Act: -0.0002

Data Index: 1579020 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9306. Min Act: -0.0002

Data Index: 1517227 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9365. Min Act: -0.0002

Data Index: 1655839 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9254. Min Act: -0.0002

Data Index: 1538504 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9331. Min Act: -0.0002

Data Index: 1451002 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9007. Min Act: -0.0002

Data Index: 1591235 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9358. Min Act: -0.0002

Data Index: 1469667 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9184. Min Act: -0.0002

Data Index: 1554503 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9212. Min Act: -0.0002

Data Index: 1421565 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9017. Min Act: -0.0002

Data Index: 1485236 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9023. Min Act: -0.0002

Data Index: 1535546 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.1142. Min Range: -1.1142

Max Act: 0.9141. Min Act: -0.0002

Data Index: 1635402 (Python Code)

Max Activating Token Index: 882