Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4468958 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0786. Min Act: -0.1700
Data Index: 7004686 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0786. Min Act: -0.1700
Data Index: 398920 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0786. Min Act: -0.1700
Data Index: 586694 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0473. Min Act: -0.1700
Data Index: 6891849 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2115413 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2516500 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0161. Min Act: -0.1700
Data Index: 317739 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0161. Min Act: -0.1700
Data Index: 3086282 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1098. Min Range: -6.1098
Max Act: 6.0161. Min Act: -0.1700
Data Index: 4602459 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9848. Min Act: -0.1700
Data Index: 8250334 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9848. Min Act: -0.1700
Data Index: 1959504 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9536. Min Act: -0.1700
Data Index: 316222 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9848. Min Act: -0.1700
Data Index: 1066660 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9848. Min Act: -0.1700
Data Index: 6446876 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9223. Min Act: -0.1700
Data Index: 2974077 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9848. Min Act: -0.1700
Data Index: 2996869 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9536. Min Act: -0.1700
Data Index: 1959503 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9536. Min Act: -0.1700
Data Index: 5584147 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1098. Min Range: -6.1098
Max Act: 5.9536. Min Act: -0.1700
Data Index: 5330719 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19