Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2539 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.7741. Min Act: -0.1700
Data Index: 4746821 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.2429. Min Act: -0.1700
Data Index: 1053555 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.2116. Min Act: -0.1700
Data Index: 5574304 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.1804. Min Act: -0.1700
Data Index: 6835968 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.1491. Min Act: -0.1700
Data Index: 3735647 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.1491. Min Act: -0.1700
Data Index: 6607213 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.1179. Min Act: -0.1700
Data Index: 3714342 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.0241. Min Act: -0.1700
Data Index: 1283262 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.0241. Min Act: -0.1700
Data Index: 3574213 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7741. Min Range: -8.7741
Max Act: 8.0241. Min Act: -0.1700
Data Index: 6607210 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.9929. Min Act: -0.1700
Data Index: 3714341 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.9616. Min Act: -0.1700
Data Index: 7711323 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.9616. Min Act: -0.1700
Data Index: 3564508 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.9304. Min Act: -0.1700
Data Index: 2737899 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.8679. Min Act: -0.1700
Data Index: 1525857 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.9304. Min Act: -0.1700
Data Index: 126050 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.8991. Min Act: -0.1700
Data Index: 5955680 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.8991. Min Act: -0.1700
Data Index: 2891750 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.8366. Min Act: -0.1700
Data Index: 2392545 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7741. Min Range: -8.7741
Max Act: 7.8366. Min Act: -0.1700
Data Index: 849837 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19