Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3620. Min Range: -7.3620
Max Act: 7.3620. Min Act: -0.1700
Data Index: 1642371 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3620. Min Range: -7.3620
Max Act: 7.2370. Min Act: -0.1700
Data Index: 1352144 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9870. Min Act: -0.1700
Data Index: 7816207 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9870. Min Act: -0.1700
Data Index: 5029659 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9245. Min Act: -0.1700
Data Index: 8033840 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9245. Min Act: -0.1700
Data Index: 5962477 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9245. Min Act: -0.1700
Data Index: 3119597 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.8933. Min Act: -0.1700
Data Index: 4565132 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.8933. Min Act: -0.1700
Data Index: 2437846 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.9245. Min Act: -0.1700
Data Index: 8828706 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.8308. Min Act: -0.1700
Data Index: 2066653 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.8308. Min Act: -0.1700
Data Index: 7643887 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7936441 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.8308. Min Act: -0.1700
Data Index: 8350391 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 398007 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 6678086 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7490669 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 6975453 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7995. Min Act: -0.1700
Data Index: 8259736 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3620. Min Range: -7.3620
Max Act: 6.7683. Min Act: -0.1700
Data Index: 768803 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19