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

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

Neuron 3096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1396157 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1624409 (Python Code)

Max Activating Token Index: 535

Text #2

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1612090 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1654073 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1398185 (Python Code)

Max Activating Token Index: 190

Text #5

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1482093 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1490689 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1577518 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1398039 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1483547 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1475040 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1464235 (Python Code)

Max Activating Token Index: 723

Text #12

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1538981 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1527103 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1463932 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1655804 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 1.4617. Min Range: -1.4617

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1473521 (Python Code)

Max Activating Token Index: 683

Text #17

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1372741 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1479073 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 1.4617. Min Range: -1.4617

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1640349 (Python Code)

Max Activating Token Index: 187