Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1847 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0363. Min Range: -7.0363
Max Act: 7.0363. Min Act: -0.1700
Data Index: 1785679 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.9426. Min Act: -0.1700
Data Index: 8463048 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.8801. Min Act: -0.1700
Data Index: 2465510 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.8488. Min Act: -0.1700
Data Index: 3219619 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7863. Min Act: -0.1700
Data Index: 6212436 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7863. Min Act: -0.1700
Data Index: 699401 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 4647213 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7863. Min Act: -0.1700
Data Index: 3901 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.6926. Min Act: -0.1700
Data Index: 1134547 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7551. Min Act: -0.1700
Data Index: 4738323 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7551. Min Act: -0.1700
Data Index: 3365329 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 5943629 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 3394941 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 6437247 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 7892267 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.6926. Min Act: -0.1700
Data Index: 3667047 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.7238. Min Act: -0.1700
Data Index: 1799223 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.6301. Min Act: -0.1700
Data Index: 225237 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.6613. Min Act: -0.1700
Data Index: 3034525 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0363. Min Range: -7.0363
Max Act: 6.6301. Min Act: -0.1700
Data Index: 2957478 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19