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

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

Neuron 1960 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.3663. Min Act: -0.0001

Data Index: 837349 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.5211. Min Act: -0.0001

Data Index: 860861 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2582. Min Act: -0.0001

Data Index: 865863 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2844. Min Act: -0.0001

Data Index: 7554 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2110. Min Act: -0.0001

Data Index: 849099 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1244. Min Act: -0.0001

Data Index: 146184 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1595. Min Act: -0.0001

Data Index: 330174 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1365. Min Act: -0.0001

Data Index: 1226831 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.1100. Min Act: -0.0001

Data Index: 239824 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0995. Min Act: -0.0001

Data Index: 43748 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.2011. Min Act: -0.0001

Data Index: 468012 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0817. Min Act: -0.0001

Data Index: 184757 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.5211. Min Range: -1.5211

Max Act: 1.0437. Min Act: -0.0001

Data Index: 801326 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9962. Min Act: -0.0001

Data Index: 944900 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9559. Min Act: -0.0001

Data Index: 634748 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9361. Min Act: -0.0001

Data Index: 35504 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9073. Min Act: -0.0001

Data Index: 186656 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.8783. Min Act: -0.0001

Data Index: 1184783 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9708. Min Act: -0.0001

Data Index: 882548 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.5211. Min Range: -1.5211

Max Act: 0.9006. Min Act: -0.0001

Data Index: 381025 (C4 (Web Text))

Max Activating Token Index: 325