Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5190 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.2614. Min Act: -0.1700
Data Index: 1923658 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.2614. Min Act: -0.1700
Data Index: 5633893 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.2614. Min Act: -0.1700
Data Index: 3743170 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.1364. Min Act: -0.1700
Data Index: 2932433 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.1364. Min Act: -0.1700
Data Index: 474010 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2614. Min Range: -8.2614
Max Act: 8.0739. Min Act: -0.1700
Data Index: 7906969 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.9801. Min Act: -0.1700
Data Index: 3443442 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.9489. Min Act: -0.1700
Data Index: 3813934 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.9489. Min Act: -0.1700
Data Index: 7458633 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.9176. Min Act: -0.1700
Data Index: 3622554 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.9176. Min Act: -0.1700
Data Index: 6426395 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8864. Min Act: -0.1700
Data Index: 7426299 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8551. Min Act: -0.1700
Data Index: 8058217 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8551. Min Act: -0.1700
Data Index: 3567134 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8239. Min Act: -0.1700
Data Index: 8669932 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8239. Min Act: -0.1700
Data Index: 27526 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.7926. Min Act: -0.1700
Data Index: 4915493 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8239. Min Act: -0.1700
Data Index: 3055838 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.8239. Min Act: -0.1700
Data Index: 6260667 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2614. Min Range: -8.2614
Max Act: 7.7614. Min Act: -0.1700
Data Index: 3010992 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19