Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6697. Min Act: -0.1700
Data Index: 5348591 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 4782914 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6385. Min Act: -0.1700
Data Index: 1271593 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6697. Min Act: -0.1700
Data Index: 7614775 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 8780013 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.6072. Min Act: -0.1700
Data Index: 4369291 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5760. Min Act: -0.1700
Data Index: 2577792 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5760. Min Act: -0.1700
Data Index: 7818618 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5760. Min Act: -0.1700
Data Index: 4489479 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5447. Min Act: -0.1700
Data Index: 7289085 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5447. Min Act: -0.1700
Data Index: 7488067 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5135. Min Act: -0.1700
Data Index: 160301 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5135. Min Act: -0.1700
Data Index: 6812128 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.5135. Min Act: -0.1700
Data Index: 4739151 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 2097793 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 5201674 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4822. Min Act: -0.1700
Data Index: 6511865 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4510. Min Act: -0.1700
Data Index: 2796458 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4197. Min Act: -0.1700
Data Index: 1358524 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6697. Min Range: -5.6697
Max Act: 5.4510. Min Act: -0.1700
Data Index: 4435049 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19