Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1738 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2394. Min Range: -5.2394
Max Act: 5.2394. Min Act: -0.1700
Data Index: 4090816 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2394. Min Range: -5.2394
Max Act: 5.2082. Min Act: -0.1700
Data Index: 3191607 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2394. Min Range: -5.2394
Max Act: 5.1144. Min Act: -0.1700
Data Index: 724721 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2394. Min Range: -5.2394
Max Act: 5.0832. Min Act: -0.1700
Data Index: 6472351 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.9894. Min Act: -0.1700
Data Index: 2625070 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.9894. Min Act: -0.1700
Data Index: 5614919 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.9582. Min Act: -0.1700
Data Index: 6274886 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8957. Min Act: -0.1700
Data Index: 4090815 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8957. Min Act: -0.1700
Data Index: 8056441 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8957. Min Act: -0.1700
Data Index: 7721601 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 1461663 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 3918973 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 6882171 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8957. Min Act: -0.1700
Data Index: 5296535 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 5994821 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 3124870 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8644. Min Act: -0.1700
Data Index: 2418642 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8332. Min Act: -0.1700
Data Index: 64118 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8332. Min Act: -0.1700
Data Index: 5051923 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2394. Min Range: -5.2394
Max Act: 4.8332. Min Act: -0.1700
Data Index: 7853726 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19