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

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

Neuron 386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1865. Min Act: -0.0000

Data Index: 898848 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1770. Min Act: -0.0001

Data Index: 269237 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1585. Min Act: -0.0000

Data Index: 34346 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1495. Min Act: -0.0001

Data Index: 877037 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1071484 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1538. Min Act: -0.0001

Data Index: 411486 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1468. Min Act: -0.0001

Data Index: 283121 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1470. Min Act: -0.0000

Data Index: 247755 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1129391 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1351. Min Act: -0.0000

Data Index: 427487 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1351787 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1328. Min Act: -0.0001

Data Index: 701166 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1276. Min Act: -0.0001

Data Index: 600717 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1301. Min Act: -0.0000

Data Index: 656014 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1264. Min Act: -0.0000

Data Index: 540645 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1024843 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1302. Min Act: -0.0000

Data Index: 589949 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1294. Min Act: -0.0000

Data Index: 224388 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1296. Min Act: -0.0001

Data Index: 169424 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.1865. Min Range: -0.1865

Max Act: 0.1208. Min Act: -0.0000

Data Index: 99080 (C4 (Web Text))

Max Activating Token Index: 345