Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.7973. Min Act: -0.1700
Data Index: 3594689 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.7660. Min Act: -0.1700
Data Index: 3572448 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.7035. Min Act: -0.1700
Data Index: 3197889 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.6723. Min Act: -0.1700
Data Index: 1754383 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.6410. Min Act: -0.1700
Data Index: 1285740 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4244827 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.4223. Min Act: -0.1700
Data Index: 1545163 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.4223. Min Act: -0.1700
Data Index: 5023804 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3910. Min Act: -0.1700
Data Index: 5435619 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3598. Min Act: -0.1700
Data Index: 3408040 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6744379 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 5301815 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 8687238 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 218036 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6271409 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.3285. Min Act: -0.1700
Data Index: 2769426 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.2973. Min Act: -0.1700
Data Index: 5048262 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.2973. Min Act: -0.1700
Data Index: 7695540 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.2660. Min Act: -0.1700
Data Index: 5816577 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7973. Min Range: -5.7973
Max Act: 5.2660. Min Act: -0.1700
Data Index: 3005597 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19