Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0001

Data Index: 1581115 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6973. Min Act: -0.0001

Data Index: 1508298 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1529112 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1428048 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7213. Min Act: -0.0001

Data Index: 1517868 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7370. Min Act: -0.0002

Data Index: 1622384 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7047. Min Act: -0.0001

Data Index: 1491202 (Python Code)

Max Activating Token Index: 801

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1489558 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6810. Min Act: -0.0001

Data Index: 1580126 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1591061 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1652920 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1439357 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6895. Min Act: -0.0001

Data Index: 1380199 (Python Code)

Max Activating Token Index: 335

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1546982 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1501092 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1375788 (Python Code)

Max Activating Token Index: 92

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1483162 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7435. Min Act: -0.0001

Data Index: 1536600 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1517732 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1600286 (Python Code)

Max Activating Token Index: 954