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

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

Neuron 79 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: 0.2493. Min Range: -0.2493

Max Act: 0.2242. Min Act: -0.0001

Data Index: 463627 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2493. Min Act: -0.0001

Data Index: 33532 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1161650 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.2017. Min Act: -0.0001

Data Index: 1183011 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1758. Min Act: -0.0001

Data Index: 61173 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1237749 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1853. Min Act: -0.0001

Data Index: 40070 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1899. Min Act: -0.0001

Data Index: 29729 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1198668 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1601. Min Act: -0.0001

Data Index: 993331 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1691. Min Act: -0.0001

Data Index: 141477 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1306257 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1738. Min Act: -0.0001

Data Index: 238238 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1674. Min Act: -0.0001

Data Index: 838099 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1095686 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1141259 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1649. Min Act: -0.0001

Data Index: 339244 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1667. Min Act: -0.0001

Data Index: 115153 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1701. Min Act: -0.0001

Data Index: 766986 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.2493. Min Range: -0.2493

Max Act: 0.1664. Min Act: -0.0001

Data Index: 483419 (C4 (Web Text))

Max Activating Token Index: 949