Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.5406. Min Act: -0.1700
Data Index: 7887932 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.4156. Min Act: -0.1700
Data Index: 1798587 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.1031. Min Act: -0.1700
Data Index: 2110314 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.1031. Min Act: -0.1700
Data Index: 6887759 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.0406. Min Act: -0.1700
Data Index: 7302631 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.0406. Min Act: -0.1700
Data Index: 5537755 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5406. Min Range: -8.5406
Max Act: 8.0406. Min Act: -0.1700
Data Index: 4842914 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9781. Min Act: -0.1700
Data Index: 4072825 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9781. Min Act: -0.1700
Data Index: 4237092 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9156. Min Act: -0.1700
Data Index: 7352689 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9156. Min Act: -0.1700
Data Index: 4164057 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9156. Min Act: -0.1700
Data Index: 4463162 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 7447949 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.9156. Min Act: -0.1700
Data Index: 1861448 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 4614770 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 7355647 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 7196036 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 2587213 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 6995633 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5406. Min Range: -8.5406
Max Act: 7.8531. Min Act: -0.1700
Data Index: 4736368 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19