Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2743. Min Range: -8.2743
Max Act: 8.2743. Min Act: -0.1700
Data Index: 4290815 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.5868. Min Act: -0.1700
Data Index: 2457649 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.4930. Min Act: -0.1700
Data Index: 7235543 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.3680. Min Act: -0.1700
Data Index: 6577083 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.3368. Min Act: -0.1700
Data Index: 6868618 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.1805. Min Act: -0.1700
Data Index: 1506719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0868. Min Act: -0.1700
Data Index: 75484 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.1180. Min Act: -0.1700
Data Index: 8577991 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0868. Min Act: -0.1700
Data Index: 244398 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0555. Min Act: -0.1700
Data Index: 4402477 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0243. Min Act: -0.1700
Data Index: 7019357 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0243. Min Act: -0.1700
Data Index: 59625 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0243. Min Act: -0.1700
Data Index: 5023983 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9930. Min Act: -0.1700
Data Index: 5291928 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2743. Min Range: -8.2743
Max Act: 7.0243. Min Act: -0.1700
Data Index: 6047998 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9930. Min Act: -0.1700
Data Index: 2771342 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9930. Min Act: -0.1700
Data Index: 7680614 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9930. Min Act: -0.1700
Data Index: 6158525 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9618. Min Act: -0.1700
Data Index: 6185362 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2743. Min Range: -8.2743
Max Act: 6.9618. Min Act: -0.1700
Data Index: 3243189 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19