Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.7722. Min Act: -0.1700
Data Index: 1052439 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.5847. Min Act: -0.1700
Data Index: 7261244 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.5222. Min Act: -0.1700
Data Index: 882228 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.4597. Min Act: -0.1700
Data Index: 5197848 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.3972. Min Act: -0.1700
Data Index: 7285305 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.3972. Min Act: -0.1700
Data Index: 284322 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.3347. Min Act: -0.1700
Data Index: 3333714 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.3347. Min Act: -0.1700
Data Index: 1808953 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.2097. Min Act: -0.1700
Data Index: 15507 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.2097. Min Act: -0.1700
Data Index: 702298 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.2097. Min Act: -0.1700
Data Index: 1274803 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.1472. Min Act: -0.1700
Data Index: 6034347 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.1472. Min Act: -0.1700
Data Index: 4962659 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.1472. Min Act: -0.1700
Data Index: 6300435 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0847. Min Act: -0.1700
Data Index: 5033863 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0222. Min Act: -0.1700
Data Index: 1027919 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0222. Min Act: -0.1700
Data Index: 1639012 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0222. Min Act: -0.1700
Data Index: 1224532 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0222. Min Act: -0.1700
Data Index: 4430006 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7722. Min Range: -10.7722
Max Act: 10.0847. Min Act: -0.1700
Data Index: 4541225 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19