Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5816. Min Range: -2.5816
Max Act: 2.5816. Min Act: -0.1700
Data Index: 7471695 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5816. Min Range: -2.5816
Max Act: 2.2885. Min Act: -0.1700
Data Index: 489429 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5816. Min Range: -2.5816
Max Act: 2.1727. Min Act: -0.1700
Data Index: 8824517 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5816. Min Range: -2.5816
Max Act: 2.0219. Min Act: -0.1698
Data Index: 6193157 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5816. Min Range: -2.5816
Max Act: 2.0050. Min Act: -0.1700
Data Index: 6437588 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.9712. Min Act: -0.1700
Data Index: 8066861 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.9373. Min Act: -0.1700
Data Index: 8066859 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.9032. Min Act: -0.1700
Data Index: 1818527 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.9032. Min Act: -0.1700
Data Index: 7853390 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.8348. Min Act: -0.1700
Data Index: 8425487 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.8004. Min Act: -0.1700
Data Index: 5585821 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.8004. Min Act: -0.1700
Data Index: 7463878 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7832. Min Act: -0.1700
Data Index: 4429898 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7487. Min Act: -0.1700
Data Index: 8262926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7660. Min Act: -0.1699
Data Index: 5901679 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7660. Min Act: -0.1700
Data Index: 139890 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7314. Min Act: -0.1695
Data Index: 6591025 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7314. Min Act: -0.1700
Data Index: 7947504 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7314. Min Act: -0.1700
Data Index: 8066860 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5816. Min Range: -2.5816
Max Act: 1.7314. Min Act: -0.1700
Data Index: 2624772 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19