Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5154 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7161049 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7751596 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1580677 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.1029. Min Act: -0.1700
Data Index: 3713258 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.0717. Min Act: -0.1700
Data Index: 7010991 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.0404. Min Act: -0.1700
Data Index: 6110073 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.0092. Min Act: -0.1700
Data Index: 6276056 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1967. Min Range: -5.1967
Max Act: 5.0092. Min Act: -0.1700
Data Index: 1580679 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9779. Min Act: -0.1700
Data Index: 5896484 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9779. Min Act: -0.1700
Data Index: 5784064 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 4566811 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 1338467 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 8165871 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 8550617 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 8738817 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 2865088 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9154. Min Act: -0.1700
Data Index: 48226 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9467. Min Act: -0.1700
Data Index: 3383090 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9154. Min Act: -0.1700
Data Index: 4403724 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1967. Min Range: -5.1967
Max Act: 4.9154. Min Act: -0.1700
Data Index: 1494976 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19