Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4532 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.8274. Min Act: -0.1700
Data Index: 6843609 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.8274. Min Act: -0.1700
Data Index: 7104811 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.8274. Min Act: -0.1700
Data Index: 3680614 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.7649. Min Act: -0.1700
Data Index: 5780387 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.5774. Min Act: -0.1700
Data Index: 5488660 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.6399. Min Act: -0.1700
Data Index: 2489254 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.5774. Min Act: -0.1700
Data Index: 4992814 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.5149. Min Act: -0.1700
Data Index: 5590207 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.4524. Min Act: -0.1700
Data Index: 3639879 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.3899. Min Act: -0.1700
Data Index: 4160653 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.4524. Min Act: -0.1700
Data Index: 6184738 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.3587. Min Act: -0.1700
Data Index: 6989476 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2962. Min Act: -0.1700
Data Index: 2994886 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2962. Min Act: -0.1700
Data Index: 7701087 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2649. Min Act: -0.1700
Data Index: 8560526 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2337. Min Act: -0.1700
Data Index: 4334299 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2649. Min Act: -0.1700
Data Index: 1940640 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2337. Min Act: -0.1700
Data Index: 8823166 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2024. Min Act: -0.1700
Data Index: 2614543 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8274. Min Range: -8.8274
Max Act: 8.2337. Min Act: -0.1700
Data Index: 7845553 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19