Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0270. Min Range: -6.0270
Max Act: 6.0270. Min Act: -0.1700
Data Index: 1163523 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.9645. Min Act: -0.1700
Data Index: 3260914 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.9645. Min Act: -0.1700
Data Index: 2286661 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.9333. Min Act: -0.1700
Data Index: 3748980 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.9333. Min Act: -0.1700
Data Index: 8468094 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.9020. Min Act: -0.1700
Data Index: 5095896 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8395. Min Act: -0.1700
Data Index: 8521976 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8708. Min Act: -0.1700
Data Index: 6215785 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8395. Min Act: -0.1700
Data Index: 6279035 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8708. Min Act: -0.1700
Data Index: 8014897 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8708. Min Act: -0.1700
Data Index: 5369865 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8395. Min Act: -0.1700
Data Index: 5047805 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8083. Min Act: -0.1700
Data Index: 3378798 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8083. Min Act: -0.1700
Data Index: 1821827 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.8083. Min Act: -0.1700
Data Index: 534480 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.7770. Min Act: -0.1700
Data Index: 2695628 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.7770. Min Act: -0.1700
Data Index: 5167238 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.7458. Min Act: -0.1700
Data Index: 1502140 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.7770. Min Act: -0.1700
Data Index: 5971748 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0270. Min Range: -6.0270
Max Act: 5.7458. Min Act: -0.1700
Data Index: 4554355 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19