Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.5245. Min Act: -0.1700
Data Index: 6670238 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.4620. Min Act: -0.1700
Data Index: 4321945 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.3995. Min Act: -0.1700
Data Index: 2281965 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.3682. Min Act: -0.1700
Data Index: 5108822 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.2745. Min Act: -0.1700
Data Index: 8296465 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.2745. Min Act: -0.1700
Data Index: 7025489 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.2120. Min Act: -0.1700
Data Index: 3814496 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1807. Min Act: -0.1700
Data Index: 958365 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1807. Min Act: -0.1700
Data Index: 765068 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 8757562 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1182. Min Act: -0.1700
Data Index: 7945971 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 2637817 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 3894127 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 2126168 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 7974256 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1182. Min Act: -0.1700
Data Index: 6436656 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1495. Min Act: -0.1700
Data Index: 7297406 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.1182. Min Act: -0.1700
Data Index: 7574856 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.0870. Min Act: -0.1700
Data Index: 1490996 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5245. Min Range: -5.5245
Max Act: 5.0870. Min Act: -0.1700
Data Index: 1301116 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19