Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.6140. Min Act: -0.1700
Data Index: 6075978 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.6140. Min Act: -0.1700
Data Index: 5281793 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.4890. Min Act: -0.1700
Data Index: 7022416 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.3328. Min Act: -0.1700
Data Index: 7115797 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.3328. Min Act: -0.1700
Data Index: 1100988 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.3015. Min Act: -0.1700
Data Index: 1678902 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.3015. Min Act: -0.1700
Data Index: 1715707 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2390. Min Act: -0.1700
Data Index: 6549885 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2390. Min Act: -0.1700
Data Index: 6811721 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2390. Min Act: -0.1700
Data Index: 3850875 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2390. Min Act: -0.1700
Data Index: 2092842 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2078. Min Act: -0.1700
Data Index: 1650567 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2078. Min Act: -0.1700
Data Index: 1217337 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2078. Min Act: -0.1700
Data Index: 8153785 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2078. Min Act: -0.1700
Data Index: 4400367 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.1765. Min Act: -0.1700
Data Index: 6192341 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.1765. Min Act: -0.1700
Data Index: 634549 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.1765. Min Act: -0.1700
Data Index: 6013459 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.2078. Min Act: -0.1700
Data Index: 4899683 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6140. Min Range: -5.6140
Max Act: 5.1765. Min Act: -0.1700
Data Index: 4561966 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19