Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.8598. Min Act: -0.1700
Data Index: 5979197 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.7660. Min Act: -0.1700
Data Index: 4417939 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.7348. Min Act: -0.1700
Data Index: 3966614 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.7348. Min Act: -0.1700
Data Index: 1301497 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.7035. Min Act: -0.1700
Data Index: 1180736 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.7035. Min Act: -0.1700
Data Index: 4706994 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6723. Min Act: -0.1700
Data Index: 3721763 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6723. Min Act: -0.1700
Data Index: 8155872 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 7511240 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6098. Min Act: -0.1700
Data Index: 1832426 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 3955599 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 548440 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 2107897 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 2026459 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.6410. Min Act: -0.1700
Data Index: 8602948 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.5785. Min Act: -0.1700
Data Index: 4389084 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.5473. Min Act: -0.1700
Data Index: 5715923 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.5473. Min Act: -0.1700
Data Index: 5904805 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.5473. Min Act: -0.1700
Data Index: 7119216 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8598. Min Range: -5.8598
Max Act: 5.5473. Min Act: -0.1700
Data Index: 7374965 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19