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

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

Neuron 4433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1145. Min Range: -4.1145

Max Act: 4.1145. Min Act: -0.0000

Data Index: 706332 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.8527. Min Act: -0.0001

Data Index: 1059971 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.9504. Min Act: -0.0001

Data Index: 729797 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.8974. Min Act: -0.0001

Data Index: 909890 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.9126. Min Act: -0.0001

Data Index: 115082 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.5870. Min Act: -0.0001

Data Index: 885939 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.5523. Min Act: -0.0001

Data Index: 908204 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.5374. Min Act: -0.0001

Data Index: 275052 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.3429. Min Act: -0.0001

Data Index: 776108 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.1561. Min Act: -0.0001

Data Index: 1284575 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.3057. Min Act: -0.0001

Data Index: 999611 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.1874. Min Act: -0.0001

Data Index: 785747 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.1784. Min Act: -0.0000

Data Index: 983735 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.0013. Min Act: -0.0001

Data Index: 664608 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.1730. Min Act: -0.0001

Data Index: 356490 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.1339. Min Act: -0.0001

Data Index: 1104089 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 4.1145. Min Range: -4.1145

Max Act: 2.9774. Min Act: -0.0001

Data Index: 63089 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.0792. Min Act: -0.0001

Data Index: 1173296 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.0609. Min Act: -0.0001

Data Index: 589550 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 4.1145. Min Range: -4.1145

Max Act: 3.2386. Min Act: -0.0001

Data Index: 662485 (C4 (Web Text))

Max Activating Token Index: 516