Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.5197. Min Act: -0.1700
Data Index: 2439871 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.5509. Min Act: -0.1700
Data Index: 2705699 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.3634. Min Act: -0.1700
Data Index: 8320294 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.3322. Min Act: -0.1700
Data Index: 5689874 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.2697. Min Act: -0.1700
Data Index: 8348962 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.2384. Min Act: -0.1700
Data Index: 2505250 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.1759. Min Act: -0.1700
Data Index: 2331077 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.1447. Min Act: -0.1700
Data Index: 6344858 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.1447. Min Act: -0.1700
Data Index: 7272988 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0822. Min Act: -0.1700
Data Index: 3324939 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.1134. Min Act: -0.1700
Data Index: 2784990 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.1134. Min Act: -0.1700
Data Index: 504071 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0822. Min Act: -0.1700
Data Index: 2715282 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0822. Min Act: -0.1700
Data Index: 7875899 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0509. Min Act: -0.1700
Data Index: 6358195 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0509. Min Act: -0.1700
Data Index: 992614 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0197. Min Act: -0.1700
Data Index: 8162976 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5509. Min Range: -6.5509
Max Act: 6.0509. Min Act: -0.1700
Data Index: 6348858 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5509. Min Range: -6.5509
Max Act: 5.9884. Min Act: -0.1700
Data Index: 5331456 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5509. Min Range: -6.5509
Max Act: 5.9572. Min Act: -0.1700
Data Index: 3514956 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19