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

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

Neuron 2968 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.1643. Min Act: -0.0000

Data Index: 87047 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.0193. Min Act: -0.0000

Data Index: 321964 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.1643. Min Range: -1.1643

Max Act: 1.0592. Min Act: -0.0000

Data Index: 87894 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.9062. Min Act: -0.0000

Data Index: 183784 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.8657. Min Act: -0.0000

Data Index: 50293 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1045199 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1300266 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7326. Min Act: -0.0000

Data Index: 411088 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6796. Min Act: -0.0000

Data Index: 536292 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7282. Min Act: -0.0000

Data Index: 575849 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7371. Min Act: -0.0000

Data Index: 996409 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7822. Min Act: -0.0000

Data Index: 997754 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6696. Min Act: -0.0000

Data Index: 803485 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.7389. Min Act: -0.0000

Data Index: 85439 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6788. Min Act: -0.0000

Data Index: 6829 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6637. Min Act: -0.0000

Data Index: 351890 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6807. Min Act: -0.0000

Data Index: 239206 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6401. Min Act: -0.0000

Data Index: 564008 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6523. Min Act: -0.0000

Data Index: 402046 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.1643. Min Range: -1.1643

Max Act: 0.6438. Min Act: -0.0000

Data Index: 95764 (C4 (Web Text))

Max Activating Token Index: 898