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

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

Neuron 1022 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1259336 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1537167 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.4884. Min Act: -0.0000

Data Index: 217950 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.4410. Min Act: -0.0000

Data Index: 194020 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.3505. Min Act: -0.0000

Data Index: 559513 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.3558. Min Act: -0.0000

Data Index: 965012 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1284391 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2633. Min Act: -0.0000

Data Index: 381394 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1469894 (Python Code)

Max Activating Token Index: 778

Text #9

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2530. Min Act: -0.0000

Data Index: 195948 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1418840 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1368582 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1601628 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1656325 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1548795 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1119307 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1517092 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1652222 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0900. Min Act: -0.0000

Data Index: 867715 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1574731 (Python Code)

Max Activating Token Index: 907