Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.8620. Min Act: -0.1700
Data Index: 1569071 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.8308. Min Act: -0.1700
Data Index: 5125542 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7995. Min Act: -0.1700
Data Index: 7074122 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7683. Min Act: -0.1700
Data Index: 7500523 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7683. Min Act: -0.1700
Data Index: 2155091 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7683. Min Act: -0.1700
Data Index: 5190385 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7683. Min Act: -0.1700
Data Index: 4276373 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7953592 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7370. Min Act: -0.1700
Data Index: 6652589 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7370. Min Act: -0.1700
Data Index: 455012 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 140227 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2470989 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 4559316 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 4625252 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 8123320 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 6572024 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 5234408 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 5040614 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.7058. Min Act: -0.1700
Data Index: 3367964 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8620. Min Range: -4.8620
Max Act: 4.6745. Min Act: -0.1700
Data Index: 3384040 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19