Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5596 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.8406. Min Act: -0.1700
Data Index: 6754348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.8719. Min Act: -0.1700
Data Index: 5320608 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6844. Min Act: -0.1700
Data Index: 8809101 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6531. Min Act: -0.1700
Data Index: 3163228 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 1850103 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6531. Min Act: -0.1700
Data Index: 5086949 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.6219. Min Act: -0.1700
Data Index: 7771956 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 4478288 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 7181487 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 1472004 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 1802473 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 4652324 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 4261442 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5906. Min Act: -0.1700
Data Index: 8768268 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5594. Min Act: -0.1700
Data Index: 4677742 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5281. Min Act: -0.1700
Data Index: 3307228 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5281. Min Act: -0.1700
Data Index: 4132720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.5281. Min Act: -0.1700
Data Index: 6202533 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4969. Min Act: -0.1700
Data Index: 299594 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8719. Min Range: -4.8719
Max Act: 4.4656. Min Act: -0.1700
Data Index: 5414363 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19