Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5237 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5940. Min Range: -9.5940
Max Act: 9.5940. Min Act: -0.1700
Data Index: 7066177 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5940. Min Range: -9.5940
Max Act: 9.4065. Min Act: -0.1700
Data Index: 5519464 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5940. Min Range: -9.5940
Max Act: 9.4065. Min Act: -0.1700
Data Index: 5519453 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5940. Min Range: -9.5940
Max Act: 9.3440. Min Act: -0.1700
Data Index: 7066162 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.9690. Min Act: -0.1700
Data Index: 3320952 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.9690. Min Act: -0.1700
Data Index: 2694633 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.8440. Min Act: -0.1700
Data Index: 2666850 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.8440. Min Act: -0.1700
Data Index: 8147634 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.8440. Min Act: -0.1700
Data Index: 8376354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7815. Min Act: -0.1700
Data Index: 2772406 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 5279598 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 6505026 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 2286436 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 5639920 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 4805843 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.6565. Min Act: -0.1700
Data Index: 2862080 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.7190. Min Act: -0.1700
Data Index: 5902849 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.5940. Min Act: -0.1700
Data Index: 4837690 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.5940. Min Act: -0.1700
Data Index: 2694631 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5940. Min Range: -9.5940
Max Act: 8.5315. Min Act: -0.1700
Data Index: 3320957 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19