Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5297 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.9705. Min Act: -0.1700
Data Index: 3247705 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.9392. Min Act: -0.1700
Data Index: 5584719 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.9392. Min Act: -0.1700
Data Index: 7725650 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.9080. Min Act: -0.1700
Data Index: 6564124 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.9080. Min Act: -0.1700
Data Index: 5584716 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8767. Min Act: -0.1700
Data Index: 5584723 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8767. Min Act: -0.1700
Data Index: 5584695 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8767. Min Act: -0.1700
Data Index: 6479423 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8454. Min Act: -0.1700
Data Index: 8809776 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8454. Min Act: -0.1700
Data Index: 8639958 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8454. Min Act: -0.1700
Data Index: 5584692 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8454. Min Act: -0.1700
Data Index: 3868758 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8454. Min Act: -0.1700
Data Index: 5086676 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.8142. Min Act: -0.1700
Data Index: 5584699 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7829. Min Act: -0.1700
Data Index: 740068 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7829. Min Act: -0.1700
Data Index: 3868791 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7829. Min Act: -0.1700
Data Index: 3662052 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7829. Min Act: -0.1700
Data Index: 8755977 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7516. Min Act: -0.1700
Data Index: 7557669 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9705. Min Range: -3.9705
Max Act: 3.7516. Min Act: -0.1700
Data Index: 5904736 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19