Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.8114. Min Act: -0.1700
Data Index: 5509279 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.6864. Min Act: -0.1700
Data Index: 7491961 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.5614. Min Act: -0.1700
Data Index: 6592980 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.4989. Min Act: -0.1700
Data Index: 4802806 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.4364. Min Act: -0.1700
Data Index: 5475366 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.3114. Min Act: -0.1700
Data Index: 4424652 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.3114. Min Act: -0.1700
Data Index: 6044139 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.3114. Min Act: -0.1700
Data Index: 3834527 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.3114. Min Act: -0.1700
Data Index: 8207535 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.2489. Min Act: -0.1700
Data Index: 5794578 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.2177. Min Act: -0.1700
Data Index: 3894061 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.1864. Min Act: -0.1700
Data Index: 7115969 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.1864. Min Act: -0.1700
Data Index: 2140173 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.1552. Min Act: -0.1700
Data Index: 1695830 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0614. Min Act: -0.1700
Data Index: 94666 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0614. Min Act: -0.1700
Data Index: 3961142 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0614. Min Act: -0.1700
Data Index: 5219011 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0614. Min Act: -0.1700
Data Index: 1252903 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0614. Min Act: -0.1700
Data Index: 5606121 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8114. Min Range: -8.8114
Max Act: 8.0302. Min Act: -0.1700
Data Index: 4173249 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19