Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2155 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0891. Min Range: -6.0891
Max Act: 6.0891. Min Act: -0.1700
Data Index: 5193193 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.9641. Min Act: -0.1700
Data Index: 2188199 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.9016. Min Act: -0.1700
Data Index: 2250838 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7141. Min Act: -0.1700
Data Index: 1531280 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7454. Min Act: -0.1700
Data Index: 5359589 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7454. Min Act: -0.1700
Data Index: 6765096 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7141. Min Act: -0.1700
Data Index: 743309 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6572081 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6820887 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6829. Min Act: -0.1700
Data Index: 5427381 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6516. Min Act: -0.1700
Data Index: 7938238 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6516. Min Act: -0.1700
Data Index: 6124634 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6204. Min Act: -0.1700
Data Index: 5960697 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6204. Min Act: -0.1700
Data Index: 3165891 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4963201 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.5891. Min Act: -0.1700
Data Index: 3599677 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.5891. Min Act: -0.1700
Data Index: 4447206 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.5891. Min Act: -0.1700
Data Index: 981961 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.5579. Min Act: -0.1700
Data Index: 8100423 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0891. Min Range: -6.0891
Max Act: 5.5579. Min Act: -0.1700
Data Index: 4478979 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19