Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.2027. Min Act: -0.1700
Data Index: 300895 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.1715. Min Act: -0.1700
Data Index: 5193634 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.1090. Min Act: -0.1698
Data Index: 1706088 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0777. Min Act: -0.1700
Data Index: 6835945 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4060500 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0465. Min Act: -0.1700
Data Index: 5255731 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0465. Min Act: -0.1700
Data Index: 510805 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0152. Min Act: -0.1700
Data Index: 7757257 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0152. Min Act: -0.1700
Data Index: 4101279 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 7222820 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 3475301 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 4962634 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 1564030 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 4608536 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6884425 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0152. Min Act: -0.1700
Data Index: 8404568 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2027. Min Range: -5.2027
Max Act: 5.0152. Min Act: -0.1700
Data Index: 5884524 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9527. Min Act: -0.1700
Data Index: 8662438 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9215. Min Act: -0.1700
Data Index: 7218440 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2027. Min Range: -5.2027
Max Act: 4.9215. Min Act: -0.1700
Data Index: 1549811 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19