Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.7353. Min Act: -0.1700
Data Index: 4073991 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.4853. Min Act: -0.1700
Data Index: 6992431 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.3603. Min Act: -0.1700
Data Index: 2227620 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2978. Min Act: -0.1700
Data Index: 6210124 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2978. Min Act: -0.1700
Data Index: 6020732 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2978. Min Act: -0.1700
Data Index: 4372375 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2665. Min Act: -0.1700
Data Index: 6938088 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2665. Min Act: -0.1700
Data Index: 4698512 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3600024 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 3740273 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 249492 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 3346296 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 5418503 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 686190 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2040. Min Act: -0.1700
Data Index: 8501001 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 4197248 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 5558076 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 2918126 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3499993 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1657854 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19