Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2160 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.4888. Min Act: -0.1700
Data Index: 5891160 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.4263. Min Act: -0.1700
Data Index: 2717373 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.3638. Min Act: -0.1700
Data Index: 3119314 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.3013. Min Act: -0.1700
Data Index: 4387338 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.2700. Min Act: -0.1700
Data Index: 2059508 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.2075. Min Act: -0.1700
Data Index: 4731552 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.1762. Min Act: -0.1700
Data Index: 5957377 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.1450. Min Act: -0.1700
Data Index: 8588217 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0825. Min Act: -0.1700
Data Index: 5361861 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0825. Min Act: -0.1700
Data Index: 2489843 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0825. Min Act: -0.1700
Data Index: 364478 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0825. Min Act: -0.1700
Data Index: 5550411 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 3039178 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 302629 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 8297955 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0825. Min Act: -0.1700
Data Index: 4145856 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 3594754 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 6203229 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0512. Min Act: -0.1700
Data Index: 2750133 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4888. Min Range: -4.4888
Max Act: 4.0200. Min Act: -0.1700
Data Index: 3873815 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19