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

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

Neuron 1904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1459386 (Python Code)

Max Activating Token Index: 886

Text #1

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.9404. Min Act: -0.0001

Data Index: 1537516 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1499545 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1542959 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1444832 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1553870 (Python Code)

Max Activating Token Index: 971

Text #6

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1608994 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8460. Min Act: -0.0001

Data Index: 1572379 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8158. Min Act: -0.0001

Data Index: 1444892 (Python Code)

Max Activating Token Index: 839

Text #9

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1515504 (Python Code)

Max Activating Token Index: 309

Text #10

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1523587 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7594. Min Act: -0.0001

Data Index: 1410926 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8106. Min Act: -0.0001

Data Index: 1570979 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1477915 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7658. Min Act: -0.0001

Data Index: 1547182 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7641. Min Act: -0.0001

Data Index: 1363998 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1580252 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7841. Min Act: -0.0001

Data Index: 1578131 (Python Code)

Max Activating Token Index: 384

Text #18

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1613657 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.9404. Min Range: -0.9404

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1640658 (Python Code)

Max Activating Token Index: 900