Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.5612. Min Act: -0.1700
Data Index: 1278465 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.4362. Min Act: -0.1700
Data Index: 8503233 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.3112. Min Act: -0.1700
Data Index: 2525736 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.3112. Min Act: -0.1700
Data Index: 5290055 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.2487. Min Act: -0.1700
Data Index: 5498418 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.2487. Min Act: -0.1700
Data Index: 8661378 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.2487. Min Act: -0.1700
Data Index: 4865058 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1862. Min Act: -0.1700
Data Index: 4136270 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.2487. Min Act: -0.1700
Data Index: 224819 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 6588036 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 6910714 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 1466797 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 919604 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 5417939 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 6262310 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 6368354 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.1237. Min Act: -0.1700
Data Index: 804851 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 8051655 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 8226211 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5612. Min Range: -9.5612
Max Act: 9.0612. Min Act: -0.1700
Data Index: 4136718 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19