Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2307. Min Range: -9.2307
Max Act: 9.2307. Min Act: -0.1700
Data Index: 8077633 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2307. Min Range: -9.2307
Max Act: 9.1057. Min Act: -0.1700
Data Index: 6479336 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2307. Min Range: -9.2307
Max Act: 9.0432. Min Act: -0.1700
Data Index: 4060501 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2307. Min Range: -9.2307
Max Act: 9.0432. Min Act: -0.1700
Data Index: 3274258 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.8557. Min Act: -0.1700
Data Index: 5061807 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.8557. Min Act: -0.1700
Data Index: 2585125 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.7307. Min Act: -0.1700
Data Index: 1987856 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.7307. Min Act: -0.1700
Data Index: 7943185 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.7307. Min Act: -0.1700
Data Index: 951769 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.7307. Min Act: -0.1700
Data Index: 5980622 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 2415763 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 3464497 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 458578 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 5429487 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 877613 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.6057. Min Act: -0.1700
Data Index: 270989 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.5432. Min Act: -0.1700
Data Index: 2911813 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.4807. Min Act: -0.1700
Data Index: 7310867 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.4807. Min Act: -0.1700
Data Index: 2221102 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2307. Min Range: -9.2307
Max Act: 8.4807. Min Act: -0.1700
Data Index: 3815955 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19