Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5938. Min Act: -0.1700
Data Index: 2214398 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5625. Min Act: -0.1700
Data Index: 6286369 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7862031 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5313. Min Act: -0.1700
Data Index: 2424089 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5000. Min Act: -0.1700
Data Index: 291258 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.5000. Min Act: -0.1700
Data Index: 4436870 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4688. Min Act: -0.1700
Data Index: 5650970 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4688. Min Act: -0.1700
Data Index: 4947325 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4375. Min Act: -0.1700
Data Index: 4842485 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4063. Min Act: -0.1700
Data Index: 5170947 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4375. Min Act: -0.1700
Data Index: 62283 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4375. Min Act: -0.1700
Data Index: 4573485 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.4375. Min Act: -0.1700
Data Index: 88209 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 919497 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 6782517 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3438. Min Act: -0.1700
Data Index: 4879228 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 1072725 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 3184362 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 80738 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5938. Min Range: -5.5938
Max Act: 5.3750. Min Act: -0.1700
Data Index: 995654 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19