Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.3127. Min Act: -0.1700
Data Index: 4542436 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.3440. Min Act: -0.1700
Data Index: 5615191 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.2502. Min Act: -0.1700
Data Index: 6665637 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.2502. Min Act: -0.1700
Data Index: 3985212 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.1877. Min Act: -0.1700
Data Index: 7134665 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.1252. Min Act: -0.1700
Data Index: 2825250 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.1252. Min Act: -0.1700
Data Index: 2917419 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3440. Min Range: -6.3440
Max Act: 6.0002. Min Act: -0.1700
Data Index: 8706362 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6776094 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.9065. Min Act: -0.1700
Data Index: 427234 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.8752. Min Act: -0.1700
Data Index: 8657451 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5960616 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.8752. Min Act: -0.1700
Data Index: 7188185 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7815. Min Act: -0.1700
Data Index: 5213729 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7815. Min Act: -0.1700
Data Index: 3682513 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7815. Min Act: -0.1700
Data Index: 2191512 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7815. Min Act: -0.1700
Data Index: 5975682 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7190. Min Act: -0.1700
Data Index: 448440 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7502. Min Act: -0.1700
Data Index: 1326236 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3440. Min Range: -6.3440
Max Act: 5.7190. Min Act: -0.1700
Data Index: 1660249 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19