Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2962 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9468. Min Act: -0.1700
Data Index: 5319170 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9468. Min Act: -0.1700
Data Index: 907961 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9155. Min Act: -0.1700
Data Index: 7823794 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9468. Min Act: -0.1700
Data Index: 907962 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9468. Min Act: -0.1700
Data Index: 1346128 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9155. Min Act: -0.1700
Data Index: 8165793 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.9155. Min Act: -0.1700
Data Index: 2419911 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.8843. Min Act: -0.1700
Data Index: 3114621 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.8218. Min Act: -0.1700
Data Index: 89061 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.7593. Min Act: -0.1700
Data Index: 4974504 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.7593. Min Act: -0.1700
Data Index: 8497220 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.7280. Min Act: -0.1700
Data Index: 3006982 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.7280. Min Act: -0.1700
Data Index: 2419908 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6968. Min Act: -0.1700
Data Index: 7131162 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6655. Min Act: -0.1700
Data Index: 7458807 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6655. Min Act: -0.1700
Data Index: 3984774 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6343. Min Act: -0.1700
Data Index: 4110779 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6030. Min Act: -0.1700
Data Index: 6737200 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6343. Min Act: -0.1700
Data Index: 365713 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9468. Min Range: -4.9468
Max Act: 4.6343. Min Act: -0.1700
Data Index: 654005 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19