Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.1891. Min Act: -0.0001

Data Index: 306458 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.1371. Min Act: -0.0001

Data Index: 1070267 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.1187. Min Act: -0.0001

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0556. Min Act: -0.0001

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0398. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0211. Min Act: -0.0001

Data Index: 1145567 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0869. Min Act: -0.0001

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0398. Min Act: -0.0001

Data Index: 829914 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0565. Min Act: -0.0001

Data Index: 161318 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 1.1891. Min Range: -1.1891

Max Act: 1.0215. Min Act: -0.0001

Data Index: 290651 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.9790. Min Act: -0.0001

Data Index: 874781 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.9292. Min Act: -0.0001

Data Index: 1256634 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8475. Min Act: -0.0001

Data Index: 1180982 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.9047. Min Act: -0.0001

Data Index: 1260647 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8609. Min Act: -0.0001

Data Index: 1066670 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8718. Min Act: -0.0001

Data Index: 893329 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8871. Min Act: -0.0001

Data Index: 617248 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8846. Min Act: -0.0001

Data Index: 1351836 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.1891. Min Range: -1.1891

Max Act: 0.8556. Min Act: -0.0001

Data Index: 542741 (C4 (Web Text))

Max Activating Token Index: 434