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

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

Neuron 4539 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: 1.0266. Min Range: -1.0266

Max Act: 1.0266. Min Act: -0.0001

Data Index: 162966 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9266. Min Act: -0.0001

Data Index: 542909 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9929. Min Act: -0.0001

Data Index: 1067708 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 1.0266. Min Range: -1.0266

Max Act: 1.0040. Min Act: -0.0001

Data Index: 761952 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.0266. Min Range: -1.0266

Max Act: 1.0021. Min Act: -0.0001

Data Index: 924166 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9918. Min Act: -0.0001

Data Index: 169221 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1074029 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9225. Min Act: -0.0001

Data Index: 529310 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9709. Min Act: -0.0001

Data Index: 1101221 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1017398 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9945. Min Act: -0.0001

Data Index: 537857 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9493. Min Act: -0.0001

Data Index: 480655 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1140668 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1065604 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8827. Min Act: -0.0001

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9501. Min Act: -0.0001

Data Index: 1010808 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8774. Min Act: -0.0001

Data Index: 791117 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8995. Min Act: -0.0001

Data Index: 416352 (C4 (Web Text))

Max Activating Token Index: 128