Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.1337. Min Act: -0.1700
Data Index: 379476 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.1337. Min Act: -0.1700
Data Index: 1454837 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.0712. Min Act: -0.1700
Data Index: 5433516 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.0712. Min Act: -0.1700
Data Index: 4281918 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.0087. Min Act: -0.1700
Data Index: 2686200 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.0087. Min Act: -0.1699
Data Index: 323928 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1337. Min Range: -7.1337
Max Act: 7.0087. Min Act: -0.1700
Data Index: 5708919 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 7989525 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 963043 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 5283859 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 3407984 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 4307057 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.9462. Min Act: -0.1700
Data Index: 1544261 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 2590696 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 733675 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 964707 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 4893797 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 5000311 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 1003131 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1337. Min Range: -7.1337
Max Act: 6.8837. Min Act: -0.1700
Data Index: 2932799 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19