Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3032 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.5480. Min Act: -0.0001
Data Index: 1355468 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2849. Min Act: -0.0001
Data Index: 1428072 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2808. Min Act: -0.0001
Data Index: 1170591 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2404. Min Act: -0.0001
Data Index: 1648853 (Python Code)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2435. Min Act: -0.0001
Data Index: 1024248 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1017. Min Act: -0.0001
Data Index: 1165890 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2846. Min Act: -0.0001
Data Index: 860583 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2857. Min Act: -0.0001
Data Index: 1470050 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1712. Min Act: -0.0001
Data Index: 319285 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2950. Min Act: -0.0001
Data Index: 69419 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.0551. Min Act: -0.0001
Data Index: 855142 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1427. Min Act: -0.0001
Data Index: 1560908 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1746. Min Act: -0.0001
Data Index: 1628153 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2244. Min Act: -0.0001
Data Index: 1250247 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2465. Min Act: -0.0001
Data Index: 532435 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.0390. Min Act: -0.0001
Data Index: 77389 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.2103. Min Act: -0.0001
Data Index: 844929 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1830. Min Act: -0.0001
Data Index: 850028 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1196. Min Act: -0.0001
Data Index: 1379820 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5480. Min Range: -1.5480
Max Act: 1.1749. Min Act: -0.0001
Data Index: 970997 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19