Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.4632. Min Act: -0.1700
Data Index: 5288420 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.4007. Min Act: -0.1700
Data Index: 4395035 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.2132. Min Act: -0.1700
Data Index: 5666171 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.0569. Min Act: -0.1700
Data Index: 4023212 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.0569. Min Act: -0.1700
Data Index: 4298843 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.0569. Min Act: -0.1700
Data Index: 5617232 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4632. Min Range: -8.4632
Max Act: 8.0569. Min Act: -0.1700
Data Index: 1067820 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9632. Min Act: -0.1700
Data Index: 2491297 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9319. Min Act: -0.1700
Data Index: 7939010 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9944. Min Act: -0.1700
Data Index: 3305772 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9007. Min Act: -0.1700
Data Index: 7948780 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8382. Min Act: -0.1700
Data Index: 970131 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8694. Min Act: -0.1700
Data Index: 5610473 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8382. Min Act: -0.1700
Data Index: 1648975 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9007. Min Act: -0.1700
Data Index: 624627 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.9007. Min Act: -0.1700
Data Index: 2080267 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8382. Min Act: -0.1700
Data Index: 4574165 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8382. Min Act: -0.1700
Data Index: 338960 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.8069. Min Act: -0.1700
Data Index: 5228442 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4632. Min Range: -8.4632
Max Act: 7.7757. Min Act: -0.1700
Data Index: 4275774 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19