Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6049 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7581. Min Act: -0.1700
Data Index: 2792403 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7408. Min Act: -0.1700
Data Index: 4950626 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7408. Min Act: -0.1700
Data Index: 2423721 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7235. Min Act: -0.1700
Data Index: 763684 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7235. Min Act: -0.1700
Data Index: 130715 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7062. Min Act: -0.1700
Data Index: 368774 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.7062. Min Act: -0.1700
Data Index: 1520600 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6975. Min Act: -0.1700
Data Index: 3170172 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6975. Min Act: -0.1700
Data Index: 5360721 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6975. Min Act: -0.1700
Data Index: 4666037 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6802. Min Act: -0.1700
Data Index: 3779342 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 5662883 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6802. Min Act: -0.1700
Data Index: 5422575 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6802. Min Act: -0.1700
Data Index: 4749251 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6802. Min Act: -0.1700
Data Index: 792506 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 5281893 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 4626551 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 2600405 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 173169 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7581. Min Range: -1.7581
Max Act: 1.6715. Min Act: -0.1700
Data Index: 6522361 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19