Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1423 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2895. Min Range: -6.2895
Max Act: 6.2895. Min Act: -0.1700
Data Index: 629242 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2895. Min Range: -6.2895
Max Act: 6.1020. Min Act: -0.1700
Data Index: 2130664 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2895. Min Range: -6.2895
Max Act: 6.0395. Min Act: -0.1700
Data Index: 1163869 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2895. Min Range: -6.2895
Max Act: 6.0707. Min Act: -0.1700
Data Index: 6363685 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9770. Min Act: -0.1700
Data Index: 6134298 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9770. Min Act: -0.1700
Data Index: 5074772 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9457. Min Act: -0.1700
Data Index: 856369 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9457. Min Act: -0.1700
Data Index: 1815215 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9145. Min Act: -0.1700
Data Index: 3643690 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.9145. Min Act: -0.1700
Data Index: 6398009 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8832. Min Act: -0.1700
Data Index: 4861543 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8520. Min Act: -0.1700
Data Index: 7570848 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8520. Min Act: -0.1700
Data Index: 6945934 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8520. Min Act: -0.1700
Data Index: 4984750 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8207. Min Act: -0.1700
Data Index: 668931 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8207. Min Act: -0.1700
Data Index: 4587763 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2077603 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8207. Min Act: -0.1700
Data Index: 8301943 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.8207. Min Act: -0.1700
Data Index: 5597857 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2895. Min Range: -6.2895
Max Act: 5.7895. Min Act: -0.1700
Data Index: 2607497 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19