Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.9709. Min Act: -0.1700
Data Index: 7083370 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.8771. Min Act: -0.1700
Data Index: 5526885 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.7834. Min Act: -0.1700
Data Index: 1495076 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.7834. Min Act: -0.1700
Data Index: 6543666 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.7521. Min Act: -0.1700
Data Index: 2827121 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.6896. Min Act: -0.1700
Data Index: 8192416 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5959. Min Act: -0.1700
Data Index: 834769 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5959. Min Act: -0.1700
Data Index: 1540691 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5959. Min Act: -0.1700
Data Index: 4752477 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5959. Min Act: -0.1700
Data Index: 2555548 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5646. Min Act: -0.1700
Data Index: 8753229 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5334. Min Act: -0.1700
Data Index: 1408831 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5646. Min Act: -0.1700
Data Index: 7018645 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5646. Min Act: -0.1700
Data Index: 8796341 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5646. Min Act: -0.1700
Data Index: 6054702 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5959. Min Act: -0.1700
Data Index: 3540340 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5646. Min Act: -0.1700
Data Index: 5783381 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5334. Min Act: -0.1700
Data Index: 2225406 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5334. Min Act: -0.1700
Data Index: 7645157 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9709. Min Range: -4.9709
Max Act: 4.5334. Min Act: -0.1700
Data Index: 5016924 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19