Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6705. Min Range: -7.6705
Max Act: 7.6705. Min Act: -0.1700
Data Index: 5131848 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6705. Min Range: -7.6705
Max Act: 7.5455. Min Act: -0.1700
Data Index: 5885677 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6705. Min Range: -7.6705
Max Act: 7.1080. Min Act: -0.1700
Data Index: 1162182 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6705. Min Range: -7.6705
Max Act: 7.1080. Min Act: -0.1700
Data Index: 4461369 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.9830. Min Act: -0.1700
Data Index: 8782516 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.9830. Min Act: -0.1700
Data Index: 7228066 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.9517. Min Act: -0.1700
Data Index: 3197187 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.9205. Min Act: -0.1700
Data Index: 6493617 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.9205. Min Act: -0.1700
Data Index: 2005052 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.8892. Min Act: -0.1700
Data Index: 690007 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.7642. Min Act: -0.1700
Data Index: 2847995 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.7330. Min Act: -0.1700
Data Index: 6860038 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.7017. Min Act: -0.1700
Data Index: 6052656 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.7330. Min Act: -0.1700
Data Index: 1003049 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6705. Min Act: -0.1700
Data Index: 2287908 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6705. Min Act: -0.1700
Data Index: 5180305 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6392. Min Act: -0.1700
Data Index: 476016 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6392. Min Act: -0.1700
Data Index: 4311011 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6392. Min Act: -0.1700
Data Index: 8207915 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6705. Min Range: -7.6705
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2566321 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19