Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.7770. Min Act: -0.1700
Data Index: 2676986 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.6330. Min Act: -0.1700
Data Index: 3327007 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5847. Min Act: -0.1700
Data Index: 3273381 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5525. Min Act: -0.1700
Data Index: 4627829 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5525. Min Act: -0.1700
Data Index: 7445794 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5525. Min Act: -0.1700
Data Index: 5594093 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5363. Min Act: -0.1700
Data Index: 2938017 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5202. Min Act: -0.1700
Data Index: 1181151 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5363. Min Act: -0.1700
Data Index: 1702539 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5202. Min Act: -0.1700
Data Index: 2576083 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5202. Min Act: -0.1700
Data Index: 460785 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5040. Min Act: -0.1700
Data Index: 3370211 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.5040. Min Act: -0.1700
Data Index: 1206465 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4878. Min Act: -0.1700
Data Index: 6330474 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4878. Min Act: -0.1700
Data Index: 7310313 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4715. Min Act: -0.1700
Data Index: 3503233 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4553. Min Act: -0.1700
Data Index: 7510449 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4390. Min Act: -0.1700
Data Index: 6943912 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4227. Min Act: -0.1700
Data Index: 945182 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7770. Min Range: -2.7770
Max Act: 2.4064. Min Act: -0.1700
Data Index: 1011153 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19