Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.5524. Min Act: -0.1700
Data Index: 7684755 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.2399. Min Act: -0.1700
Data Index: 1167848 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.2399. Min Act: -0.1700
Data Index: 6212262 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.2087. Min Act: -0.1700
Data Index: 105321 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.2087. Min Act: -0.1700
Data Index: 7392333 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.2399. Min Act: -0.1700
Data Index: 3799262 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1774. Min Act: -0.1700
Data Index: 5426369 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1462. Min Act: -0.1700
Data Index: 3921728 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1462. Min Act: -0.1700
Data Index: 8211479 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1774. Min Act: -0.1700
Data Index: 611206 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1462. Min Act: -0.1700
Data Index: 506043 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1149. Min Act: -0.1700
Data Index: 1104886 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.1149. Min Act: -0.1700
Data Index: 1469388 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0837. Min Act: -0.1700
Data Index: 7392772 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0837. Min Act: -0.1700
Data Index: 1136931 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0837. Min Act: -0.1700
Data Index: 6751831 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0524. Min Act: -0.1700
Data Index: 4471751 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0212. Min Act: -0.1700
Data Index: 3849337 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0524. Min Act: -0.1700
Data Index: 599889 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5524. Min Range: -5.5524
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5822770 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19