Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0839. Min Range: -6.0839
Max Act: 6.0839. Min Act: -0.1700
Data Index: 2810803 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.9901. Min Act: -0.1700
Data Index: 2483824 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.9901. Min Act: -0.1700
Data Index: 7334526 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.9589. Min Act: -0.1700
Data Index: 365169 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.8651. Min Act: -0.1700
Data Index: 7720334 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.8651. Min Act: -0.1700
Data Index: 189861 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.8026. Min Act: -0.1700
Data Index: 6332011 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.8026. Min Act: -0.1700
Data Index: 1762791 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7714. Min Act: -0.1700
Data Index: 8234186 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7401. Min Act: -0.1700
Data Index: 6288491 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7401. Min Act: -0.1700
Data Index: 5113139 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7401. Min Act: -0.1700
Data Index: 7680115 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7089. Min Act: -0.1700
Data Index: 7225830 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7401. Min Act: -0.1700
Data Index: 1762792 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.7401. Min Act: -0.1700
Data Index: 1611201 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.6464. Min Act: -0.1700
Data Index: 4990947 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.6151. Min Act: -0.1700
Data Index: 8514302 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.6151. Min Act: -0.1700
Data Index: 2061904 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.5839. Min Act: -0.1700
Data Index: 3305039 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0839. Min Range: -6.0839
Max Act: 5.5526. Min Act: -0.1700
Data Index: 3820085 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19