Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5984 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.5290. Min Act: -0.1700
Data Index: 7630783 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 5523459 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 4646249 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.2790. Min Act: -0.1700
Data Index: 1981636 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.2477. Min Act: -0.1700
Data Index: 6384092 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.2165. Min Act: -0.1700
Data Index: 2529779 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.0602. Min Act: -0.1700
Data Index: 2543014 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9977. Min Act: -0.1700
Data Index: 5301533 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.0290. Min Act: -0.1700
Data Index: 4084170 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9977. Min Act: -0.1700
Data Index: 5301531 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9977. Min Act: -0.1700
Data Index: 2863528 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6969089 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9352. Min Act: -0.1700
Data Index: 4922707 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9352. Min Act: -0.1700
Data Index: 7133062 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9352. Min Act: -0.1700
Data Index: 7551153 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9040. Min Act: -0.1700
Data Index: 5601809 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 7316345 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.8727. Min Act: -0.1700
Data Index: 2744308 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.9040. Min Act: -0.1700
Data Index: 3803222 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5290. Min Range: -5.5290
Max Act: 4.8415. Min Act: -0.1700
Data Index: 1514528 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19