Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1119371 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1233. Min Act: -0.0001

Data Index: 32055 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1062827 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1294731 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1374. Min Act: -0.0001

Data Index: 812835 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1129. Min Act: -0.0001

Data Index: 27465 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1254. Min Act: -0.0001

Data Index: 382455 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1214. Min Act: -0.0001

Data Index: 749695 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1100568 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0953. Min Act: -0.0001

Data Index: 170721 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1017. Min Act: -0.0001

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0985. Min Act: -0.0001

Data Index: 185074 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1095603 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0916. Min Act: -0.0001

Data Index: 179912 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0895. Min Act: -0.0001

Data Index: 737283 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0858. Min Act: -0.0001

Data Index: 982711 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1348774 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1111. Min Act: -0.0001

Data Index: 138801 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0948. Min Act: -0.0001

Data Index: 7798 (C4 (Web Text))

Max Activating Token Index: 429