Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.6646. Min Act: -0.1700
Data Index: 3779915 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.4146. Min Act: -0.1700
Data Index: 3640189 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.3521. Min Act: -0.1700
Data Index: 8764831 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.2271. Min Act: -0.1700
Data Index: 281312 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.1021. Min Act: -0.1700
Data Index: 4062501 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.1021. Min Act: -0.1700
Data Index: 5294650 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.0396. Min Act: -0.1700
Data Index: 2590750 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6646. Min Range: -8.6646
Max Act: 8.0396. Min Act: -0.1700
Data Index: 1303876 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9771. Min Act: -0.1700
Data Index: 4025380 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9771. Min Act: -0.1700
Data Index: 7888581 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9146. Min Act: -0.1700
Data Index: 3766861 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9146. Min Act: -0.1700
Data Index: 4881285 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9146. Min Act: -0.1700
Data Index: 3299888 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.9146. Min Act: -0.1700
Data Index: 3834235 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.8521. Min Act: -0.1700
Data Index: 590181 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.8521. Min Act: -0.1700
Data Index: 3450714 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.7896. Min Act: -0.1700
Data Index: 4150638 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.7896. Min Act: -0.1700
Data Index: 2339390 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.7271. Min Act: -0.1700
Data Index: 6087454 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6646. Min Range: -8.6646
Max Act: 7.6646. Min Act: -0.1700
Data Index: 3630209 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19