Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1661 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.8497. Min Act: -0.1700
Data Index: 1504854 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.6935. Min Act: -0.1700
Data Index: 2640821 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.6622. Min Act: -0.1700
Data Index: 8081258 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.6622. Min Act: -0.1700
Data Index: 4517168 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.5372. Min Act: -0.1700
Data Index: 5928280 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.5685. Min Act: -0.1700
Data Index: 6165290 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.5372. Min Act: -0.1700
Data Index: 3723817 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4747. Min Act: -0.1700
Data Index: 3855959 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.5060. Min Act: -0.1700
Data Index: 5762134 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4747. Min Act: -0.1700
Data Index: 317352 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4747. Min Act: -0.1700
Data Index: 360557 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4435. Min Act: -0.1700
Data Index: 1193634 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4747. Min Act: -0.1700
Data Index: 291060 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.4122. Min Act: -0.1700
Data Index: 1088694 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3810. Min Act: -0.1700
Data Index: 5153558 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3810. Min Act: -0.1700
Data Index: 2640820 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3810. Min Act: -0.1700
Data Index: 6137390 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3497. Min Act: -0.1700
Data Index: 6045122 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3810. Min Act: -0.1700
Data Index: 4676374 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8497. Min Range: -5.8497
Max Act: 5.3810. Min Act: -0.1700
Data Index: 6141324 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19