Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 541 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1659. Min Act: -0.1700
Data Index: 136298 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1659. Min Act: -0.1700
Data Index: 918813 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1493. Min Act: -0.1700
Data Index: 1124778 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1659. Min Act: -0.1700
Data Index: 1188442 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1493. Min Act: -0.1700
Data Index: 1300840 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1493. Min Act: -0.1700
Data Index: 799268 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1493. Min Act: -0.1700
Data Index: 1212116 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 73910 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 930432 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 133720 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1159. Min Act: -0.1700
Data Index: 1132596 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1159. Min Act: -0.1700
Data Index: 535297 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 199447 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 647098 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1159. Min Act: -0.1700
Data Index: 871581 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 487409 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1326. Min Act: -0.1700
Data Index: 383981 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1159. Min Act: -0.1700
Data Index: 1564237 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.0992. Min Act: -0.1700
Data Index: 146786 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1659. Min Range: -2.1659
Max Act: 2.1159. Min Act: -0.1700
Data Index: 157636 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19