Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.2950. Min Act: -0.1700
Data Index: 8795269 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.3263. Min Act: -0.1700
Data Index: 7614469 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.2325. Min Act: -0.1700
Data Index: 2592244 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.2013. Min Act: -0.1700
Data Index: 5185335 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.1388. Min Act: -0.1700
Data Index: 4402234 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.0763. Min Act: -0.1700
Data Index: 3016140 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3263. Min Range: -7.3263
Max Act: 7.0450. Min Act: -0.1700
Data Index: 6275838 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.9825. Min Act: -0.1700
Data Index: 3862937 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.8575. Min Act: -0.1700
Data Index: 1525583 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.8575. Min Act: -0.1700
Data Index: 1097559 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.8263. Min Act: -0.1700
Data Index: 4221843 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.8263. Min Act: -0.1700
Data Index: 3446374 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.8263. Min Act: -0.1700
Data Index: 5068926 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.7950. Min Act: -0.1700
Data Index: 6574756 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.7638. Min Act: -0.1700
Data Index: 8465922 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.7638. Min Act: -0.1700
Data Index: 8095047 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.7013. Min Act: -0.1700
Data Index: 5152553 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.7325. Min Act: -0.1700
Data Index: 5045600 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.6700. Min Act: -0.1700
Data Index: 2541746 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3263. Min Range: -7.3263
Max Act: 6.6700. Min Act: -0.1700
Data Index: 5992497 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19