Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.1916. Min Act: -0.1700
Data Index: 8714641 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.1916. Min Act: -0.1700
Data Index: 6778390 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 1791364 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.0041. Min Act: -0.1700
Data Index: 4229018 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.0041. Min Act: -0.1700
Data Index: 4405875 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1916. Min Range: -9.1916
Max Act: 9.0041. Min Act: -0.1700
Data Index: 6754125 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.9416. Min Act: -0.1700
Data Index: 2799433 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.9416. Min Act: -0.1700
Data Index: 1129522 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8791. Min Act: -0.1700
Data Index: 2414464 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8791. Min Act: -0.1700
Data Index: 4892756 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8791. Min Act: -0.1700
Data Index: 281258 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8791. Min Act: -0.1700
Data Index: 1333344 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.7541. Min Act: -0.1700
Data Index: 5540395 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8166. Min Act: -0.1700
Data Index: 5461069 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.7541. Min Act: -0.1700
Data Index: 3139969 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.7541. Min Act: -0.1700
Data Index: 8333745 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.8166. Min Act: -0.1700
Data Index: 2705575 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.7541. Min Act: -0.1700
Data Index: 2447463 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.7541. Min Act: -0.1700
Data Index: 8332586 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1916. Min Range: -9.1916
Max Act: 8.6916. Min Act: -0.1700
Data Index: 2549236 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19