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

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

Neuron 2511 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: 0.1919. Min Range: -0.1919

Max Act: 0.1919. Min Act: -0.0001

Data Index: 290425 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1734. Min Act: -0.0001

Data Index: 957869 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1744. Min Act: -0.0001

Data Index: 269552 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1675. Min Act: -0.0001

Data Index: 840939 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1643. Min Act: -0.0001

Data Index: 773804 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1636. Min Act: -0.0001

Data Index: 214859 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1581. Min Act: -0.0001

Data Index: 403603 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1512. Min Act: -0.0001

Data Index: 243677 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1559. Min Act: -0.0001

Data Index: 357047 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1564. Min Act: -0.0001

Data Index: 994151 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1029415 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1553. Min Act: -0.0001

Data Index: 183450 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1526. Min Act: -0.0001

Data Index: 228090 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1319782 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1512. Min Act: -0.0001

Data Index: 628590 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1444. Min Act: -0.0001

Data Index: 243856 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1504. Min Act: -0.0001

Data Index: 141360 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1497. Min Act: -0.0001

Data Index: 563214 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1498. Min Act: -0.0001

Data Index: 47723 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.1919. Min Range: -0.1919

Max Act: 0.1482. Min Act: -0.0001

Data Index: 5749 (C4 (Web Text))

Max Activating Token Index: 28