Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5794 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3891. Min Act: -0.1700
Data Index: 5218937 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3579. Min Act: -0.1700
Data Index: 6631684 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2954. Min Act: -0.1700
Data Index: 1047221 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2954. Min Act: -0.1700
Data Index: 5672322 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2329. Min Act: -0.1700
Data Index: 7190295 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2329. Min Act: -0.1700
Data Index: 33738 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2329. Min Act: -0.1700
Data Index: 6486662 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2016. Min Act: -0.1700
Data Index: 8261159 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1704. Min Act: -0.1700
Data Index: 7412031 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1704. Min Act: -0.1700
Data Index: 2606253 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1391. Min Act: -0.1700
Data Index: 157869 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1079. Min Act: -0.1700
Data Index: 6048158 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 4594545 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 2713067 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 8506980 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0766. Min Act: -0.1700
Data Index: 2933186 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0141. Min Act: -0.1700
Data Index: 8090987 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0454. Min Act: -0.1700
Data Index: 6155092 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.0141. Min Act: -0.1700
Data Index: 8493436 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3891. Min Range: -6.3891
Max Act: 5.9829. Min Act: -0.1700
Data Index: 4294938 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19