Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.1043. Min Act: -0.1700
Data Index: 7578038 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.1043. Min Act: -0.1700
Data Index: 359200 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0412. Min Act: -0.1700
Data Index: 1372986 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0254. Min Act: -0.1700
Data Index: 719800 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0254. Min Act: -0.1700
Data Index: 6339502 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0412. Min Act: -0.1700
Data Index: 8098331 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0254. Min Act: -0.1700
Data Index: 2720540 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1043. Min Range: -3.1043
Max Act: 3.0096. Min Act: -0.1700
Data Index: 7695258 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9780. Min Act: -0.1700
Data Index: 561691 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9780. Min Act: -0.1700
Data Index: 1854847 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9780. Min Act: -0.1700
Data Index: 7195745 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9780. Min Act: -0.1700
Data Index: 8270506 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9938. Min Act: -0.1700
Data Index: 8516085 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9622. Min Act: -0.1700
Data Index: 5670812 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9622. Min Act: -0.1700
Data Index: 4638261 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9622. Min Act: -0.1700
Data Index: 1854848 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9622. Min Act: -0.1700
Data Index: 2871519 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9305. Min Act: -0.1700
Data Index: 2698112 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9305. Min Act: -0.1700
Data Index: 6183689 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1043. Min Range: -3.1043
Max Act: 2.9305. Min Act: -0.1700
Data Index: 5465216 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19