Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4155 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.7995. Min Act: -0.1700
Data Index: 4742390 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.6120. Min Act: -0.1700
Data Index: 7219108 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.3620. Min Act: -0.1700
Data Index: 4620440 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.4245. Min Act: -0.1700
Data Index: 8497954 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.1745. Min Act: -0.1700
Data Index: 3398867 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7995. Min Range: -8.7995
Max Act: 8.0495. Min Act: -0.1700
Data Index: 7623551 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.9870. Min Act: -0.1700
Data Index: 2877795 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.9870. Min Act: -0.1700
Data Index: 2290623 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.9245. Min Act: -0.1700
Data Index: 5064945 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.9245. Min Act: -0.1700
Data Index: 1385349 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 3082197 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.8620. Min Act: -0.1700
Data Index: 7164738 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.8620. Min Act: -0.1700
Data Index: 3653808 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.8620. Min Act: -0.1700
Data Index: 7258495 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.8620. Min Act: -0.1700
Data Index: 6688630 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 3338279 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.8620. Min Act: -0.1700
Data Index: 2916098 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 2806100 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 7541761 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7995. Min Range: -8.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 7587277 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19