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

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

Neuron 5736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.8709. Min Act: -0.0000

Data Index: 1125997 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.5787. Min Act: -0.0001

Data Index: 855709 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.2002. Min Act: -0.0000

Data Index: 837869 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.0478. Min Act: -0.0001

Data Index: 550777 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.8111. Min Act: -0.0000

Data Index: 1130148 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.0119. Min Act: -0.0001

Data Index: 678637 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.8888. Min Act: -0.0000

Data Index: 40816 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.9942. Min Act: -0.0000

Data Index: 550832 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 2.8709. Min Range: -2.8709

Max Act: 2.0620. Min Act: -0.0001

Data Index: 328538 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.8283. Min Act: -0.0000

Data Index: 54492 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.8682. Min Act: -0.0001

Data Index: 737085 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.8434. Min Act: -0.0000

Data Index: 740069 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.7946. Min Act: -0.0001

Data Index: 1188715 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.9829. Min Act: -0.0000

Data Index: 257588 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.6822. Min Act: -0.0000

Data Index: 722972 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.9782. Min Act: -0.0000

Data Index: 537471 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.6547. Min Act: -0.0001

Data Index: 418937 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.5101. Min Act: -0.0001

Data Index: 300323 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1107816 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 2.8709. Min Range: -2.8709

Max Act: 1.5861. Min Act: -0.0001

Data Index: 296378 (C4 (Web Text))

Max Activating Token Index: 115