Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1072 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0052. Min Range: -5.0052
Max Act: 5.0052. Min Act: -0.1700
Data Index: 1848693 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0052. Min Range: -5.0052
Max Act: 5.0052. Min Act: -0.1700
Data Index: 2191842 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.9740. Min Act: -0.1700
Data Index: 7229231 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.9427. Min Act: -0.1700
Data Index: 7367554 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.9427. Min Act: -0.1700
Data Index: 8369570 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.9115. Min Act: -0.1700
Data Index: 1068165 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.8802. Min Act: -0.1700
Data Index: 5198532 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.8802. Min Act: -0.1700
Data Index: 5893580 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.8490. Min Act: -0.1700
Data Index: 3821061 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7865. Min Act: -0.1700
Data Index: 7998630 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7865. Min Act: -0.1700
Data Index: 8263474 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7865. Min Act: -0.1700
Data Index: 6741752 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7865. Min Act: -0.1700
Data Index: 6048927 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7865. Min Act: -0.1700
Data Index: 229836 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7552. Min Act: -0.1700
Data Index: 5958 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7240. Min Act: -0.1700
Data Index: 4742131 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7552. Min Act: -0.1700
Data Index: 8286585 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7552. Min Act: -0.1700
Data Index: 6945484 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.7552. Min Act: -0.1700
Data Index: 520051 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0052. Min Range: -5.0052
Max Act: 4.6927. Min Act: -0.1700
Data Index: 4118778 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19