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

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

Neuron 4489 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.9975. Min Act: -0.0000

Data Index: 820406 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.6908. Min Act: -0.0000

Data Index: 1087513 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.1060. Min Act: -0.0000

Data Index: 141256 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1245158 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0632. Min Act: -0.0000

Data Index: 985446 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0593. Min Act: -0.0000

Data Index: 950044 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0544. Min Act: -0.0000

Data Index: 7473 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0420. Min Act: -0.0000

Data Index: 7519 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0612. Min Act: -0.0000

Data Index: 781809 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0799. Min Act: -0.0000

Data Index: 375271 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9978. Min Act: -0.0000

Data Index: 542767 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0049. Min Act: -0.0000

Data Index: 594318 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9424. Min Act: -0.0000

Data Index: 225224 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9938. Min Act: -0.0000

Data Index: 369610 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9935. Min Act: -0.0000

Data Index: 111686 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.9975. Min Range: -1.9975

Max Act: 1.0494. Min Act: -0.0000

Data Index: 855407 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9708. Min Act: -0.0000

Data Index: 987509 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9570. Min Act: -0.0000

Data Index: 876247 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1315282 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.9975. Min Range: -1.9975

Max Act: 0.9996. Min Act: -0.0000

Data Index: 624111 (C4 (Web Text))

Max Activating Token Index: 250