Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5740 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.3001. Min Act: -0.1700
Data Index: 3255852 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0813. Min Act: -0.1700
Data Index: 8183135 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0813. Min Act: -0.1700
Data Index: 180657 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0813. Min Act: -0.1700
Data Index: 1222743 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0813. Min Act: -0.1700
Data Index: 2252019 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0501. Min Act: -0.1700
Data Index: 740521 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0188. Min Act: -0.1700
Data Index: 1153616 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9876. Min Act: -0.1700
Data Index: 4405495 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9563. Min Act: -0.1700
Data Index: 224104 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9563. Min Act: -0.1700
Data Index: 740524 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9563. Min Act: -0.1700
Data Index: 5573140 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9563. Min Act: -0.1700
Data Index: 6692883 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9563. Min Act: -0.1700
Data Index: 626123 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9251. Min Act: -0.1700
Data Index: 5482240 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9251. Min Act: -0.1700
Data Index: 8204830 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 740520 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 5411367 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 6469979 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 1076581 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8626. Min Act: -0.1700
Data Index: 3120148 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19