Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.9221. Min Act: -0.1700
Data Index: 7704011 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.8284. Min Act: -0.1700
Data Index: 4897294 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.8284. Min Act: -0.1700
Data Index: 3013497 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7971. Min Act: -0.1700
Data Index: 2434852 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7659. Min Act: -0.1700
Data Index: 4961546 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7346. Min Act: -0.1700
Data Index: 4410531 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7034. Min Act: -0.1700
Data Index: 4877902 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6721. Min Act: -0.1700
Data Index: 7929240 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7034. Min Act: -0.1700
Data Index: 4417447 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 8778800 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.7034. Min Act: -0.1700
Data Index: 1363410 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 1939500 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6721. Min Act: -0.1700
Data Index: 775992 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 8135270 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 7050374 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 132737 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6096. Min Act: -0.1700
Data Index: 8254362 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6409. Min Act: -0.1700
Data Index: 3528219 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.6096. Min Act: -0.1700
Data Index: 104090 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9221. Min Range: -6.9221
Max Act: 6.5784. Min Act: -0.1700
Data Index: 5650229 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19