Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1936 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.9914. Min Act: -0.1700
Data Index: 8600963 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.8351. Min Act: -0.1700
Data Index: 4661526 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.8351. Min Act: -0.1700
Data Index: 4310356 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.7101. Min Act: -0.1700
Data Index: 4171331 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6476. Min Act: -0.1700
Data Index: 3659384 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6476. Min Act: -0.1700
Data Index: 3659386 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6476. Min Act: -0.1700
Data Index: 6803527 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6789. Min Act: -0.1700
Data Index: 7209277 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6476. Min Act: -0.1700
Data Index: 7209278 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6476. Min Act: -0.1700
Data Index: 1314979 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.5851. Min Act: -0.1700
Data Index: 4622349 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6164. Min Act: -0.1700
Data Index: 7209279 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.6164. Min Act: -0.1700
Data Index: 5721057 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.5851. Min Act: -0.1700
Data Index: 3324773 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.5226. Min Act: -0.1700
Data Index: 6082959 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.4914. Min Act: -0.1700
Data Index: 1548657 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.5226. Min Act: -0.1700
Data Index: 3659385 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.4914. Min Act: -0.1700
Data Index: 3659389 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.5226. Min Act: -0.1700
Data Index: 5292969 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9914. Min Range: -6.9914
Max Act: 6.4914. Min Act: -0.1700
Data Index: 3659391 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19