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

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

Neuron 2625 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: 1.9741. Min Range: -1.9741

Max Act: 1.9741. Min Act: -0.0001

Data Index: 677544 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.8871. Min Act: -0.0001

Data Index: 511488 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.4487. Min Act: -0.0001

Data Index: 563837 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.3224. Min Act: -0.0001

Data Index: 139018 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.1973. Min Act: -0.0001

Data Index: 912115 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.1833. Min Act: -0.0001

Data Index: 1010576 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.1515. Min Act: -0.0001

Data Index: 218932 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.2105. Min Act: -0.0001

Data Index: 743974 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.1123. Min Act: -0.0001

Data Index: 21943 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.0972. Min Act: -0.0001

Data Index: 1262849 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.9522. Min Act: -0.0001

Data Index: 83146 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.9795. Min Act: -0.0001

Data Index: 924970 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.8561. Min Act: -0.0001

Data Index: 485675 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.9311. Min Act: -0.0001

Data Index: 339339 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.8806. Min Act: -0.0001

Data Index: 388987 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.9150. Min Act: -0.0001

Data Index: 1342814 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.9741. Min Range: -1.9741

Max Act: 1.0084. Min Act: -0.0001

Data Index: 1034514 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.8341. Min Act: -0.0001

Data Index: 377266 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.8520. Min Act: -0.0001

Data Index: 1255741 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.9741. Min Range: -1.9741

Max Act: 0.8769. Min Act: -0.0001

Data Index: 1000714 (C4 (Web Text))

Max Activating Token Index: 232