Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4387 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3115. Min Range: -7.3115
Max Act: 7.3115. Min Act: -0.1700
Data Index: 1688017 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3115. Min Range: -7.3115
Max Act: 7.2490. Min Act: -0.1700
Data Index: 1037738 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.9677. Min Act: -0.1700
Data Index: 2783585 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.8740. Min Act: -0.1700
Data Index: 2225819 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.8427. Min Act: -0.1700
Data Index: 5456797 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.8115. Min Act: -0.1700
Data Index: 3758379 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.8115. Min Act: -0.1700
Data Index: 5196469 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.7802. Min Act: -0.1700
Data Index: 5840835 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.7490. Min Act: -0.1700
Data Index: 3381896 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.7490. Min Act: -0.1700
Data Index: 4269145 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.7177. Min Act: -0.1700
Data Index: 553745 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.7490. Min Act: -0.1700
Data Index: 2934856 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.6552. Min Act: -0.1700
Data Index: 3654374 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.6865. Min Act: -0.1700
Data Index: 2560174 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.6865. Min Act: -0.1700
Data Index: 5379178 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.6865. Min Act: -0.1700
Data Index: 3921717 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.5615. Min Act: -0.1700
Data Index: 262889 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.5615. Min Act: -0.1700
Data Index: 5031907 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.5615. Min Act: -0.1700
Data Index: 523521 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3115. Min Range: -7.3115
Max Act: 6.5302. Min Act: -0.1700
Data Index: 4663702 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19