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

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

Neuron 2682 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: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0000

Data Index: 50354 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1097288 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0990. Min Act: -0.0000

Data Index: 482227 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1299704 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1090. Min Act: -0.0000

Data Index: 253713 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1083942 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0965. Min Act: -0.0001

Data Index: 227538 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0884. Min Act: -0.0000

Data Index: 744235 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1046921 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0897. Min Act: -0.0000

Data Index: 997581 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0877. Min Act: -0.0001

Data Index: 297571 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0852. Min Act: -0.0000

Data Index: 114136 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0817. Min Act: -0.0001

Data Index: 905064 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0813. Min Act: -0.0001

Data Index: 695631 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1065122 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1008730 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0888. Min Act: -0.0001

Data Index: 323349 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0881. Min Act: -0.0000

Data Index: 178371 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0760. Min Act: -0.0001

Data Index: 661338 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0815. Min Act: -0.0000

Data Index: 24071 (C4 (Web Text))

Max Activating Token Index: 875