Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.9048. Min Act: -0.1700
Data Index: 1099308 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.8735. Min Act: -0.1700
Data Index: 1847305 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.7798. Min Act: -0.1700
Data Index: 1015968 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.7798. Min Act: -0.1700
Data Index: 236266 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.7485. Min Act: -0.1700
Data Index: 2863424 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6860. Min Act: -0.1700
Data Index: 4687384 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6860. Min Act: -0.1700
Data Index: 2141143 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6548. Min Act: -0.1700
Data Index: 8200113 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6548. Min Act: -0.1700
Data Index: 5694980 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6235. Min Act: -0.1700
Data Index: 1162555 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.6235. Min Act: -0.1700
Data Index: 2843699 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.5298. Min Act: -0.1700
Data Index: 3907502 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4985. Min Act: -0.1700
Data Index: 4633851 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.5298. Min Act: -0.1700
Data Index: 8156794 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1366596 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4985. Min Act: -0.1700
Data Index: 1328683 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.5298. Min Act: -0.1700
Data Index: 3452215 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4673. Min Act: -0.1700
Data Index: 5023763 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4673. Min Act: -0.1700
Data Index: 6074011 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9048. Min Range: -6.9048
Max Act: 6.4673. Min Act: -0.1700
Data Index: 3264208 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19