Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4750. Min Range: -5.4750
Max Act: 5.4750. Min Act: -0.1700
Data Index: 1353313 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4750. Min Range: -5.4750
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5555464 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.8500. Min Act: -0.1700
Data Index: 7439336 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.8813. Min Act: -0.1700
Data Index: 6690140 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.9125. Min Act: -0.1700
Data Index: 6673408 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.8813. Min Act: -0.1700
Data Index: 83870 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.8500. Min Act: -0.1700
Data Index: 8165550 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.8500. Min Act: -0.1700
Data Index: 3360570 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 7913818 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 6478008 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 3526653 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 3757334 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7875. Min Act: -0.1700
Data Index: 2163487 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 3922265 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 4406139 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7563. Min Act: -0.1700
Data Index: 1731615 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.6938. Min Act: -0.1700
Data Index: 650761 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 7501290 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.7250. Min Act: -0.1700
Data Index: 2343154 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4750. Min Range: -5.4750
Max Act: 4.6625. Min Act: -0.1700
Data Index: 571519 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19