Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.8755. Min Act: -0.1700
Data Index: 7689475 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.8130. Min Act: -0.1700
Data Index: 4613670 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.6880. Min Act: -0.1700
Data Index: 1235474 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.6255. Min Act: -0.1700
Data Index: 573437 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.6255. Min Act: -0.1700
Data Index: 3883654 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3755. Min Act: -0.1700
Data Index: 6645404 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.4380. Min Act: -0.1700
Data Index: 8408885 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3755. Min Act: -0.1700
Data Index: 1835391 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 7312161 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 7940898 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.2818. Min Act: -0.1700
Data Index: 3523453 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 570974 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 8236156 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.3130. Min Act: -0.1700
Data Index: 4501040 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.2818. Min Act: -0.1700
Data Index: 749709 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1880. Min Act: -0.1700
Data Index: 5691142 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.2193. Min Act: -0.1700
Data Index: 4720261 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.1880. Min Act: -0.1700
Data Index: 1788604 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.2193. Min Act: -0.1700
Data Index: 3894392 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8755. Min Range: -8.8755
Max Act: 8.2193. Min Act: -0.1700
Data Index: 109871 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19