Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2260 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.6745. Min Act: -0.1700
Data Index: 4016013 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.6120. Min Act: -0.1700
Data Index: 2963919 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.5495. Min Act: -0.1700
Data Index: 8069969 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.6120. Min Act: -0.1700
Data Index: 2441286 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.4245. Min Act: -0.1700
Data Index: 5687239 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.3620. Min Act: -0.1700
Data Index: 8579887 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.2995. Min Act: -0.1700
Data Index: 7944091 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.2995. Min Act: -0.1700
Data Index: 1022491 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.2995. Min Act: -0.1700
Data Index: 5664615 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.2370. Min Act: -0.1700
Data Index: 5949061 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.2370. Min Act: -0.1700
Data Index: 6914484 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1745. Min Act: -0.1700
Data Index: 279205 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1745. Min Act: -0.1700
Data Index: 371950 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1745. Min Act: -0.1700
Data Index: 8436903 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1745. Min Act: -0.1700
Data Index: 1306248 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1745. Min Act: -0.1700
Data Index: 2112826 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1120. Min Act: -0.1700
Data Index: 457749 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1120. Min Act: -0.1700
Data Index: 1363609 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1120. Min Act: -0.1700
Data Index: 584565 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6745. Min Range: -9.6745
Max Act: 9.1120. Min Act: -0.1700
Data Index: 8134159 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19