Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1873 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.2805. Min Act: -0.1700
Data Index: 491200 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.2180. Min Act: -0.1700
Data Index: 415395 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.2805. Min Act: -0.1700
Data Index: 1285201 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.2805. Min Act: -0.1700
Data Index: 745517 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.1555. Min Act: -0.1700
Data Index: 322605 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.2180. Min Act: -0.1700
Data Index: 648038 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.1242. Min Act: -0.1700
Data Index: 553668 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.1242. Min Act: -0.1700
Data Index: 782544 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0929. Min Act: -0.1700
Data Index: 110598 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0617. Min Act: -0.1700
Data Index: 948165 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0929. Min Act: -0.1700
Data Index: 1512694 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2805. Min Range: -4.2805
Max Act: 3.9053. Min Act: -0.1700
Data Index: 95686 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0929. Min Act: -0.1700
Data Index: 971669 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0304. Min Act: -0.1700
Data Index: 577426 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2805. Min Range: -4.2805
Max Act: 3.9991. Min Act: -0.1700
Data Index: 30953 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0304. Min Act: -0.1700
Data Index: 640278 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0617. Min Act: -0.1700
Data Index: 1307972 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.0304. Min Act: -0.1700
Data Index: 1206109 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2805. Min Range: -4.2805
Max Act: 4.1555. Min Act: -0.1700
Data Index: 1106556 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2805. Min Range: -4.2805
Max Act: 3.9679. Min Act: -0.1700
Data Index: 808126 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19