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

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

Neuron 135 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9258. Min Act: -0.0001

Data Index: 1181869 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.7029. Min Act: -0.0001

Data Index: 582592 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.9919. Min Act: -0.0001

Data Index: 830711 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5405. Min Act: -0.0001

Data Index: 1329456 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5820. Min Act: -0.0001

Data Index: 1121042 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.4542. Min Act: -0.0001

Data Index: 399197 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6570. Min Act: -0.0001

Data Index: 553500 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.7494. Min Act: -0.0001

Data Index: 651733 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6156. Min Act: -0.0001

Data Index: 4320 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6444. Min Act: -0.0000

Data Index: 1428510 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5841. Min Act: -0.0001

Data Index: 1175711 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5715. Min Act: -0.0001

Data Index: 1141162 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6152. Min Act: -0.0001

Data Index: 867882 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.4458. Min Act: -0.0001

Data Index: 443645 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.7028. Min Act: -0.0001

Data Index: 181687 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1547188 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6422. Min Act: -0.0000

Data Index: 1582039 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.6509. Min Act: -0.0001

Data Index: 271842 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1407139 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 1.9919. Min Range: -1.9919

Max Act: 1.5725. Min Act: -0.0000

Data Index: 1457366 (Python Code)

Max Activating Token Index: 58