Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.4166. Min Act: -0.1700
Data Index: 2713070 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.3541. Min Act: -0.1700
Data Index: 155858 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.2916. Min Act: -0.1700
Data Index: 1536257 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.3541. Min Act: -0.1700
Data Index: 7289973 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.2291. Min Act: -0.1700
Data Index: 1654748 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.1666. Min Act: -0.1700
Data Index: 4858030 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4166. Min Range: -8.4166
Max Act: 8.1666. Min Act: -0.1700
Data Index: 8448063 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.9479. Min Act: -0.1700
Data Index: 1885970 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.9166. Min Act: -0.1700
Data Index: 7092202 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.8541. Min Act: -0.1700
Data Index: 2166788 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.8229. Min Act: -0.1700
Data Index: 7511006 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.7604. Min Act: -0.1700
Data Index: 2914425 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6979. Min Act: -0.1700
Data Index: 2787598 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6979. Min Act: -0.1700
Data Index: 89828 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6666. Min Act: -0.1700
Data Index: 48393 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6666. Min Act: -0.1700
Data Index: 7335858 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6354. Min Act: -0.1700
Data Index: 7741422 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6041. Min Act: -0.1700
Data Index: 7168991 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.6041. Min Act: -0.1700
Data Index: 7751568 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4166. Min Range: -8.4166
Max Act: 7.5729. Min Act: -0.1700
Data Index: 6220891 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19