Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7313. Min Act: -0.1700
Data Index: 8006326 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7313. Min Act: -0.1700
Data Index: 8763266 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7000. Min Act: -0.1700
Data Index: 1222297 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7000. Min Act: -0.1700
Data Index: 4437187 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.7000. Min Act: -0.1700
Data Index: 6945098 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.6688. Min Act: -0.1700
Data Index: 7860007 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5750. Min Act: -0.1700
Data Index: 2892741 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5750. Min Act: -0.1700
Data Index: 2897111 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5438. Min Act: -0.1700
Data Index: 6516114 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5438. Min Act: -0.1700
Data Index: 591325 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5438. Min Act: -0.1700
Data Index: 7101848 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5438. Min Act: -0.1700
Data Index: 7167123 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4553488 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1953745 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4118475 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 6637039 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 5588354 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4813. Min Act: -0.1700
Data Index: 7283516 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.4813. Min Act: -0.1700
Data Index: 4682524 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7313. Min Range: -6.7313
Max Act: 6.5125. Min Act: -0.1700
Data Index: 6851940 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19