Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1790. Min Range: -6.1790
Max Act: 6.1790. Min Act: -0.1700
Data Index: 1022573 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.7728. Min Act: -0.1700
Data Index: 8024379 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7549729 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.7415. Min Act: -0.1700
Data Index: 747100 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5414133 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.6790. Min Act: -0.1700
Data Index: 8681358 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.7103. Min Act: -0.1700
Data Index: 4375463 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5828605 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.5853. Min Act: -0.1700
Data Index: 2957925 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.6165. Min Act: -0.1700
Data Index: 8094348 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.5228. Min Act: -0.1700
Data Index: 8445740 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.5228. Min Act: -0.1700
Data Index: 6647966 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.5228. Min Act: -0.1700
Data Index: 1762923 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4915. Min Act: -0.1700
Data Index: 6263921 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4915. Min Act: -0.1700
Data Index: 1015201 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4915. Min Act: -0.1700
Data Index: 1519268 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4603. Min Act: -0.1700
Data Index: 6331229 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4603. Min Act: -0.1700
Data Index: 8070437 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4915. Min Act: -0.1700
Data Index: 5916566 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1790. Min Range: -6.1790
Max Act: 5.4290. Min Act: -0.1700
Data Index: 6896565 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19