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

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

Neuron 3070 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: 0.2117. Min Range: -0.2117

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1293171 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1882. Min Act: -0.0001

Data Index: 165067 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1821. Min Act: -0.0001

Data Index: 435578 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1692. Min Act: -0.0001

Data Index: 439076 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1700. Min Act: -0.0001

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1688. Min Act: -0.0001

Data Index: 584541 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1698. Min Act: -0.0001

Data Index: 523280 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1499. Min Act: -0.0001

Data Index: 55576 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1666. Min Act: -0.0001

Data Index: 960489 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1643. Min Act: -0.0001

Data Index: 976499 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1010106 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1495. Min Act: -0.0001

Data Index: 822575 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1497. Min Act: -0.0001

Data Index: 794668 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1439. Min Act: -0.0001

Data Index: 925010 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1510. Min Act: -0.0001

Data Index: 896906 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1526. Min Act: -0.0001

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1513. Min Act: -0.0001

Data Index: 413816 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1488. Min Act: -0.0001

Data Index: 793914 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1451. Min Act: -0.0001

Data Index: 964111 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.2117. Min Range: -0.2117

Max Act: 0.1594. Min Act: -0.0001

Data Index: 146161 (C4 (Web Text))

Max Activating Token Index: 816