Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.9596. Min Act: -0.1700
Data Index: 1618017 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.7721. Min Act: -0.1700
Data Index: 1655956 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.7096. Min Act: -0.1700
Data Index: 8517533 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.6159. Min Act: -0.1700
Data Index: 3314256 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.6159. Min Act: -0.1700
Data Index: 7253035 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.6471. Min Act: -0.1700
Data Index: 5575405 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.6159. Min Act: -0.1700
Data Index: 6689508 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.6159. Min Act: -0.1700
Data Index: 8128874 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 3849806 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 4777595 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 8121801 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 2248843 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 139339 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5534. Min Act: -0.1700
Data Index: 5420838 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.4909. Min Act: -0.1700
Data Index: 7837398 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.5221. Min Act: -0.1700
Data Index: 7564307 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.4909. Min Act: -0.1700
Data Index: 1622001 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.4909. Min Act: -0.1700
Data Index: 873598 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.4284. Min Act: -0.1700
Data Index: 7747303 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9596. Min Range: -4.9596
Max Act: 4.4596. Min Act: -0.1700
Data Index: 6855095 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19