Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 30 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2840. Min Range: -3.2840
Max Act: 3.2840. Min Act: -0.1700
Data Index: 921411 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8896. Min Act: -0.1700
Data Index: 1119424 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8896. Min Act: -0.1700
Data Index: 1409145 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8737. Min Act: -0.1700
Data Index: 37538 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8737. Min Act: -0.1700
Data Index: 1542121 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8419. Min Act: -0.1700
Data Index: 423310 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8578. Min Act: -0.1700
Data Index: 1397854 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8419. Min Act: -0.1700
Data Index: 1541432 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8260. Min Act: -0.1700
Data Index: 1328749 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8419. Min Act: -0.1700
Data Index: 1537830 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8419. Min Act: -0.1700
Data Index: 1368782 (Python Code)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8578. Min Act: -0.1700
Data Index: 1383413 (Python Code)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8419. Min Act: -0.1700
Data Index: 661301 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8260. Min Act: -0.1700
Data Index: 1407390 (Python Code)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8260. Min Act: -0.1700
Data Index: 1365482 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8260. Min Act: -0.1700
Data Index: 148050 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8101. Min Act: -0.1700
Data Index: 1599647 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8101. Min Act: -0.1700
Data Index: 777416 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.8101. Min Act: -0.1700
Data Index: 15114 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2840. Min Range: -3.2840
Max Act: 2.7942. Min Act: -0.1700
Data Index: 1618264 (Python Code)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19