Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.4895. Min Act: -0.1700
Data Index: 902787 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.3645. Min Act: -0.1700
Data Index: 8065518 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.3645. Min Act: -0.1700
Data Index: 2678398 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.2082. Min Act: -0.1700
Data Index: 6564368 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.1770. Min Act: -0.1700
Data Index: 4245746 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4895. Min Range: -6.4895
Max Act: 6.0520. Min Act: -0.1700
Data Index: 5120742 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.9895. Min Act: -0.1700
Data Index: 2954464 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.9582. Min Act: -0.1700
Data Index: 4395641 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.9270. Min Act: -0.1700
Data Index: 7245175 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.8645. Min Act: -0.1700
Data Index: 1737888 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.8645. Min Act: -0.1700
Data Index: 4619072 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.8332. Min Act: -0.1700
Data Index: 185353 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7707. Min Act: -0.1700
Data Index: 4729029 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7707. Min Act: -0.1700
Data Index: 8320355 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7395. Min Act: -0.1700
Data Index: 6065931 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7082. Min Act: -0.1700
Data Index: 1665262 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7082. Min Act: -0.1700
Data Index: 8123802 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7082. Min Act: -0.1700
Data Index: 4337233 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.7082. Min Act: -0.1700
Data Index: 81386 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4895. Min Range: -6.4895
Max Act: 5.6770. Min Act: -0.1700
Data Index: 7084987 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19