Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 6768979 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.2500. Min Act: -0.1700
Data Index: 3495099 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.1563. Min Act: -0.1700
Data Index: 5134504 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.1250. Min Act: -0.1700
Data Index: 8715930 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0938. Min Act: -0.1700
Data Index: 8731749 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0625. Min Act: -0.1700
Data Index: 4774453 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0000. Min Act: -0.1700
Data Index: 4774455 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0000. Min Act: -0.1700
Data Index: 7210868 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0000. Min Act: -0.1700
Data Index: 6436499 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2500. Min Range: -5.2500
Max Act: 5.0000. Min Act: -0.1700
Data Index: 1439111 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9688. Min Act: -0.1700
Data Index: 487396 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9688. Min Act: -0.1700
Data Index: 1757706 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9688. Min Act: -0.1700
Data Index: 6397733 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9688. Min Act: -0.1700
Data Index: 5089415 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9688. Min Act: -0.1700
Data Index: 8760534 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.9063. Min Act: -0.1700
Data Index: 214111 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.8750. Min Act: -0.1700
Data Index: 5107242 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.8750. Min Act: -0.1700
Data Index: 2196343 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.8750. Min Act: -0.1700
Data Index: 456737 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2500. Min Range: -5.2500
Max Act: 4.8750. Min Act: -0.1700
Data Index: 3971614 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19