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

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

Neuron 2961 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4063. Min Range: -4.4063

Max Act: 4.4063. Min Act: -0.0000

Data Index: 1463916 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.7158. Min Act: -0.0000

Data Index: 1405610 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.7042. Min Act: -0.0000

Data Index: 1414971 (Python Code)

Max Activating Token Index: 671

Text #3

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.6990. Min Act: -0.0000

Data Index: 1523146 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.8088. Min Act: -0.0000

Data Index: 1555576 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.4926. Min Act: -0.0000

Data Index: 1604844 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.2617. Min Act: -0.0000

Data Index: 1483290 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.2209. Min Act: -0.0000

Data Index: 1648112 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.1523. Min Act: -0.0000

Data Index: 1433293 (Python Code)

Max Activating Token Index: 323

Text #9

Max Range: 4.4063. Min Range: -4.4063

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1646259 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.1298. Min Act: -0.0000

Data Index: 1558452 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.2410. Min Act: -0.0000

Data Index: 1619645 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.2347. Min Act: -0.0000

Data Index: 1456260 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.0040. Min Act: -0.0000

Data Index: 1634849 (Python Code)

Max Activating Token Index: 363

Text #14

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.1051. Min Act: -0.0000

Data Index: 1507213 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 4.4063. Min Range: -4.4063

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1449381 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 4.4063. Min Range: -4.4063

Max Act: 2.9134. Min Act: -0.0000

Data Index: 1637508 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 4.4063. Min Range: -4.4063

Max Act: 2.9005. Min Act: -0.0000

Data Index: 1641075 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.0314. Min Act: -0.0000

Data Index: 1655135 (Python Code)

Max Activating Token Index: 141

Text #19

Max Range: 4.4063. Min Range: -4.4063

Max Act: 3.0217. Min Act: -0.0000

Data Index: 1609674 (Python Code)

Max Activating Token Index: 743