Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.9889. Min Act: -0.1700
Data Index: 3676456 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8639. Min Act: -0.1606
Data Index: 4870231 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8639. Min Act: -0.1697
Data Index: 1776477 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8326. Min Act: -0.1635
Data Index: 5703439 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8014. Min Act: -0.1698
Data Index: 4642834 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8326. Min Act: -0.1696
Data Index: 3005244 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3803644 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.7701. Min Act: -0.1626
Data Index: 7608702 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7608701 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.7076. Min Act: -0.0186
Data Index: 1960691 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6764. Min Act: -0.1681
Data Index: 3865018 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.7076. Min Act: -0.1534
Data Index: 4786411 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6764. Min Act: -0.1657
Data Index: 792291 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6764. Min Act: -0.1694
Data Index: 4642838 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6451. Min Act: -0.1700
Data Index: 3918016 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6451. Min Act: -0.1699
Data Index: 5880353 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6139. Min Act: -0.1697
Data Index: 312082 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6451. Min Act: -0.1700
Data Index: 6606048 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6451. Min Act: -0.1700
Data Index: 6473893 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9889. Min Range: -5.9889
Max Act: 5.6451. Min Act: -0.1700
Data Index: 5465993 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19