Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6079. Min Range: -10.6079
Max Act: 10.6079. Min Act: -0.1700
Data Index: 5251161 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6079. Min Range: -10.6079
Max Act: 10.4829. Min Act: -0.1700
Data Index: 4978875 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6079. Min Range: -10.6079
Max Act: 10.1704. Min Act: -0.1700
Data Index: 3434078 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6079. Min Range: -10.6079
Max Act: 10.0454. Min Act: -0.1700
Data Index: 1488616 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.9829. Min Act: -0.1700
Data Index: 3246679 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.9204. Min Act: -0.1700
Data Index: 1485450 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.8579. Min Act: -0.1700
Data Index: 7683734 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.7954. Min Act: -0.1700
Data Index: 3365601 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.6704. Min Act: -0.1700
Data Index: 319890 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.5454. Min Act: -0.1700
Data Index: 8472170 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.4829. Min Act: -0.1700
Data Index: 6050296 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.4829. Min Act: -0.1700
Data Index: 4753709 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.4829. Min Act: -0.1700
Data Index: 4139456 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.4829. Min Act: -0.1700
Data Index: 2765626 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.4204. Min Act: -0.1700
Data Index: 2440698 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.3579. Min Act: -0.1700
Data Index: 5171222 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.3579. Min Act: -0.1700
Data Index: 3541796 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.3579. Min Act: -0.1700
Data Index: 5179539 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.2954. Min Act: -0.1700
Data Index: 3741757 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6079. Min Range: -10.6079
Max Act: 9.2954. Min Act: -0.1700
Data Index: 5816567 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19