Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.5758. Min Act: -0.1700
Data Index: 2221857 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.5758. Min Act: -0.1700
Data Index: 7304489 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.5133. Min Act: -0.1700
Data Index: 5510266 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.2946. Min Act: -0.1700
Data Index: 3424519 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.2008. Min Act: -0.1700
Data Index: 3186698 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.2321. Min Act: -0.1700
Data Index: 8547982 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.2008. Min Act: -0.1700
Data Index: 2642618 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.1696. Min Act: -0.1700
Data Index: 6428844 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.1071. Min Act: -0.1700
Data Index: 5866337 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5758. Min Range: -7.5758
Max Act: 7.0446. Min Act: -0.1700
Data Index: 5107903 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.9821. Min Act: -0.1700
Data Index: 147715 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.9821. Min Act: -0.1700
Data Index: 1815873 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.9821. Min Act: -0.1700
Data Index: 4194900 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.9821. Min Act: -0.1700
Data Index: 613656 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.9508. Min Act: -0.1700
Data Index: 5681316 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.8883. Min Act: -0.1700
Data Index: 7907834 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.8258. Min Act: -0.1700
Data Index: 8612492 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.7946. Min Act: -0.1700
Data Index: 5487975 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.7946. Min Act: -0.1700
Data Index: 1777493 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5758. Min Range: -7.5758
Max Act: 6.7946. Min Act: -0.1700
Data Index: 3179449 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19