Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5640 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.3719. Min Act: -0.1699
Data Index: 196232 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.3407. Min Act: -0.1696
Data Index: 6937514 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.3094. Min Act: -0.1696
Data Index: 7913692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2782. Min Act: -0.1700
Data Index: 881795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2782. Min Act: -0.1696
Data Index: 5811001 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2469. Min Act: -0.1696
Data Index: 485709 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2469. Min Act: -0.1700
Data Index: 5387432 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2469. Min Act: -0.1700
Data Index: 3145002 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2469. Min Act: -0.1700
Data Index: 7137659 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2469. Min Act: -0.1700
Data Index: 6965698 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1844. Min Act: -0.1700
Data Index: 4813285 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2157. Min Act: -0.1700
Data Index: 6807027 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2157. Min Act: -0.1699
Data Index: 2722538 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2157. Min Act: -0.1699
Data Index: 3902890 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1844. Min Act: -0.1700
Data Index: 4179190 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1844. Min Act: -0.1700
Data Index: 5682333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.2157. Min Act: -0.1700
Data Index: 8485673 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1844. Min Act: -0.1700
Data Index: 501672 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1844. Min Act: -0.1696
Data Index: 3343195 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3719. Min Range: -6.3719
Max Act: 6.1532. Min Act: -0.1700
Data Index: 6630542 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19