Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.5268. Min Act: -0.1700
Data Index: 5773330 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.5268. Min Act: -0.1700
Data Index: 4788754 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3705. Min Act: -0.1700
Data Index: 6106636 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3705. Min Act: -0.1700
Data Index: 3361109 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3080. Min Act: -0.1700
Data Index: 8017112 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5680377 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.1830. Min Act: -0.1700
Data Index: 5313036 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.0893. Min Act: -0.1700
Data Index: 3595149 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.0893. Min Act: -0.1700
Data Index: 5429446 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.0580. Min Act: -0.1700
Data Index: 4341018 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9955. Min Act: -0.1700
Data Index: 6372319 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.0268. Min Act: -0.1700
Data Index: 7861710 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9955. Min Act: -0.1700
Data Index: 5226770 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9955. Min Act: -0.1700
Data Index: 3494446 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9643. Min Act: -0.1700
Data Index: 2357910 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9330. Min Act: -0.1700
Data Index: 4621414 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9643. Min Act: -0.1700
Data Index: 2348182 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9330. Min Act: -0.1700
Data Index: 3180145 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9330. Min Act: -0.1700
Data Index: 262678 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5268. Min Range: -6.5268
Max Act: 5.9330. Min Act: -0.1700
Data Index: 3298885 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19