Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.9629. Min Act: -0.1700
Data Index: 3090506 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.8378. Min Act: -0.1700
Data Index: 5974865 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.7753. Min Act: -0.1700
Data Index: 7463576 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2188789 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6814. Min Act: -0.1700
Data Index: 2184721 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6658. Min Act: -0.1700
Data Index: 3306020 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3865067 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6658. Min Act: -0.1700
Data Index: 6363446 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6501. Min Act: -0.1700
Data Index: 3861662 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6188. Min Act: -0.1700
Data Index: 7343203 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.6188. Min Act: -0.1700
Data Index: 2684092 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5875. Min Act: -0.1700
Data Index: 6540047 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5562. Min Act: -0.1700
Data Index: 5922057 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5562. Min Act: -0.1700
Data Index: 3040866 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5406. Min Act: -0.1700
Data Index: 95373 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5249. Min Act: -0.1700
Data Index: 3084389 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5406. Min Act: -0.1700
Data Index: 3909534 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5406. Min Act: -0.1700
Data Index: 8466355 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5249. Min Act: -0.1700
Data Index: 1415204 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9629. Min Range: -3.9629
Max Act: 3.5249. Min Act: -0.1700
Data Index: 6438692 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19