Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 684 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0002

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1006. Min Act: -0.0002

Data Index: 180595 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0967. Min Act: -0.0002

Data Index: 81893 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0954. Min Act: -0.0002

Data Index: 9368 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0923. Min Act: -0.0002

Data Index: 527880 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0888. Min Act: -0.0002

Data Index: 495378 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0917. Min Act: -0.0002

Data Index: 323439 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0884. Min Act: -0.0002

Data Index: 25163 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0840. Min Act: -0.0002

Data Index: 742620 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0851. Min Act: -0.0002

Data Index: 720841 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0830. Min Act: -0.0002

Data Index: 510464 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0850. Min Act: -0.0002

Data Index: 934093 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0840. Min Act: -0.0002

Data Index: 359401 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0842. Min Act: -0.0002

Data Index: 427881 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0836. Min Act: -0.0002

Data Index: 131722 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0833. Min Act: -0.0002

Data Index: 938090 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0842. Min Act: -0.0002

Data Index: 893421 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0841. Min Act: -0.0002

Data Index: 614514 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0867. Min Act: -0.0001

Data Index: 631466 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1211601 (C4 (Web Text))

Max Activating Token Index: 25