Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4226 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.1925. Min Act: -0.1700
Data Index: 6352636 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.2237. Min Act: -0.1700
Data Index: 583234 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0987. Min Act: -0.1700
Data Index: 1735977 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0675. Min Act: -0.1700
Data Index: 6621323 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0362. Min Act: -0.1700
Data Index: 4410284 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0050. Min Act: -0.1700
Data Index: 7860787 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0362. Min Act: -0.1700
Data Index: 3413845 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0050. Min Act: -0.1700
Data Index: 2673906 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2237. Min Range: -6.2237
Max Act: 6.0050. Min Act: -0.1700
Data Index: 1631945 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9737. Min Act: -0.1700
Data Index: 8792467 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9425. Min Act: -0.1700
Data Index: 8151696 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9112. Min Act: -0.1700
Data Index: 350938 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9737. Min Act: -0.1700
Data Index: 4941860 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9425. Min Act: -0.1700
Data Index: 6153715 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9112. Min Act: -0.1700
Data Index: 5711686 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9112. Min Act: -0.1700
Data Index: 582523 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9112. Min Act: -0.1700
Data Index: 8096353 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.8800. Min Act: -0.1700
Data Index: 1553332 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.8800. Min Act: -0.1700
Data Index: 1508046 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2237. Min Range: -6.2237
Max Act: 5.9112. Min Act: -0.1700
Data Index: 1430105 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19