Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.4087. Min Act: -0.1700
Data Index: 1957912 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.1587. Min Act: -0.1700
Data Index: 8727106 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.1275. Min Act: -0.1700
Data Index: 8118789 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.0650. Min Act: -0.1700
Data Index: 491404 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.0962. Min Act: -0.1700
Data Index: 5518082 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.0650. Min Act: -0.1700
Data Index: 4249898 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4087. Min Range: -6.4087
Max Act: 6.0025. Min Act: -0.1700
Data Index: 2695062 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.9712. Min Act: -0.1700
Data Index: 7866237 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.9400. Min Act: -0.1700
Data Index: 1971179 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.9087. Min Act: -0.1700
Data Index: 1519291 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.9087. Min Act: -0.1700
Data Index: 1525495 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.9400. Min Act: -0.1700
Data Index: 6815718 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.8775. Min Act: -0.1700
Data Index: 5629385 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.8150. Min Act: -0.1700
Data Index: 8109921 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.8150. Min Act: -0.1700
Data Index: 2952871 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.8150. Min Act: -0.1700
Data Index: 5363951 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.7837. Min Act: -0.1700
Data Index: 4299455 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.7837. Min Act: -0.1700
Data Index: 857061 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.7837. Min Act: -0.1700
Data Index: 2219717 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4087. Min Range: -6.4087
Max Act: 5.7837. Min Act: -0.1700
Data Index: 989297 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19