Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 81 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.9484. Min Act: -0.1700
Data Index: 440223 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.9326. Min Act: -0.1700
Data Index: 1167237 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.9009. Min Act: -0.1700
Data Index: 1608973 (Python Code)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8691. Min Act: -0.1700
Data Index: 253505 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8850. Min Act: -0.1700
Data Index: 340804 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8373. Min Act: -0.1700
Data Index: 468529 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8373. Min Act: -0.1700
Data Index: 1296875 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8214. Min Act: -0.1700
Data Index: 1217344 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.8214. Min Act: -0.1700
Data Index: 135112 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7896. Min Act: -0.1700
Data Index: 181989 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7896. Min Act: -0.1700
Data Index: 802645 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7737. Min Act: -0.1700
Data Index: 1269822 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7417. Min Act: -0.1700
Data Index: 148447 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7737. Min Act: -0.1700
Data Index: 1303969 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7417. Min Act: -0.1700
Data Index: 936940 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7417. Min Act: -0.1700
Data Index: 1218779 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7417. Min Act: -0.1700
Data Index: 506271 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7098. Min Act: -0.1700
Data Index: 632376 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7258. Min Act: -0.1700
Data Index: 173727 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9484. Min Range: -2.9484
Max Act: 2.7417. Min Act: -0.1700
Data Index: 1253422 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19