Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2671 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.9763. Min Act: -0.1700
Data Index: 1388428 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.9450. Min Act: -0.1700
Data Index: 4326943 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.7575. Min Act: -0.1700
Data Index: 6591078 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.7263. Min Act: -0.1700
Data Index: 6297815 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.6950. Min Act: -0.1700
Data Index: 1853446 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.6638. Min Act: -0.1700
Data Index: 2175425 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5700. Min Act: -0.1700
Data Index: 6029176 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.6325. Min Act: -0.1700
Data Index: 5215476 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5388. Min Act: -0.1700
Data Index: 2159706 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6928801 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5075. Min Act: -0.1700
Data Index: 6493956 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5388. Min Act: -0.1700
Data Index: 6664212 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5075. Min Act: -0.1700
Data Index: 7272737 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5075. Min Act: -0.1700
Data Index: 805975 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.5075. Min Act: -0.1700
Data Index: 7722803 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.4763. Min Act: -0.1700
Data Index: 6975977 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.4763. Min Act: -0.1700
Data Index: 6066013 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.4763. Min Act: -0.1700
Data Index: 5472668 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.4763. Min Act: -0.1700
Data Index: 8601569 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9763. Min Range: -6.9763
Max Act: 6.4450. Min Act: -0.1700
Data Index: 3515253 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19