Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 2432527 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5769. Min Act: -0.1700
Data Index: 6601899 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5456. Min Act: -0.1700
Data Index: 1520634 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5144. Min Act: -0.1700
Data Index: 336909 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.5144. Min Act: -0.1700
Data Index: 7083869 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 1986397 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 3379778 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 4809506 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 3508308 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 4299444 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 5704502 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 8783362 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 6871583 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 4885912 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4206. Min Act: -0.1700
Data Index: 52363 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3894. Min Act: -0.1700
Data Index: 8497116 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 5498803 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 1949395 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 201047 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.3581. Min Act: -0.1700
Data Index: 1768927 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19