Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4331 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.9761. Min Act: -0.0000

Data Index: 1150741 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 3.9761. Min Range: -3.9761

Max Act: 3.3846. Min Act: -0.0000

Data Index: 80309 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.6216. Min Act: -0.0000

Data Index: 940461 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.2050. Min Act: -0.0000

Data Index: 884589 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1773. Min Act: -0.0000

Data Index: 50654 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.5266. Min Act: -0.0000

Data Index: 704186 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.2112. Min Act: -0.0000

Data Index: 629200 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.2015. Min Act: -0.0000

Data Index: 724717 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.2023. Min Act: -0.0000

Data Index: 979444 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1601. Min Act: -0.0000

Data Index: 363297 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.3766. Min Act: -0.0000

Data Index: 490643 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.3800. Min Act: -0.0000

Data Index: 534427 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.9761. Min Range: -3.9761

Max Act: 1.9489. Min Act: -0.0000

Data Index: 68977 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.0865. Min Act: -0.0000

Data Index: 65063 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1798. Min Act: -0.0000

Data Index: 641150 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1580. Min Act: -0.0000

Data Index: 414133 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1511. Min Act: -0.0000

Data Index: 1136518 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1625. Min Act: -0.0000

Data Index: 1103494 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 3.9761. Min Range: -3.9761

Max Act: 2.1170. Min Act: -0.0000

Data Index: 457994 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.9761. Min Range: -3.9761

Max Act: 1.9952. Min Act: -0.0000

Data Index: 291699 (C4 (Web Text))

Max Activating Token Index: 904