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

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

Neuron 2709 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4854. Min Act: -0.0001

Data Index: 824694 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5377. Min Act: -0.0001

Data Index: 318022 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5107. Min Act: -0.0001

Data Index: 1273828 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5459. Min Act: -0.0001

Data Index: 156605 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5028. Min Act: -0.0001

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4800. Min Act: -0.0001

Data Index: 48681 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5135. Min Act: -0.0001

Data Index: 942245 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5400. Min Act: -0.0001

Data Index: 372797 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4870. Min Act: -0.0001

Data Index: 1305302 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5072. Min Act: -0.0001

Data Index: 430829 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1335963 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5079. Min Act: -0.0001

Data Index: 230111 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4640. Min Act: -0.0001

Data Index: 479158 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4746. Min Act: -0.0001

Data Index: 585053 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4680. Min Act: -0.0001

Data Index: 43958 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4676. Min Act: -0.0001

Data Index: 495253 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5274. Min Act: -0.0001

Data Index: 965838 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.5002. Min Act: -0.0001

Data Index: 679582 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4582. Min Act: -0.0001

Data Index: 632708 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.5459. Min Range: -0.5459

Max Act: 0.4815. Min Act: -0.0001

Data Index: 512123 (C4 (Web Text))

Max Activating Token Index: 610