Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.8552. Min Act: -0.1700
Data Index: 3678465 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 1067263 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.7927. Min Act: -0.1700
Data Index: 8274189 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 7419995 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.7302. Min Act: -0.1700
Data Index: 2338770 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.6677. Min Act: -0.1700
Data Index: 8161897 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.6677. Min Act: -0.1700
Data Index: 8686210 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.6677. Min Act: -0.1700
Data Index: 4729663 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.5427. Min Act: -0.1700
Data Index: 7757077 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.5115. Min Act: -0.1700
Data Index: 6813426 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4802. Min Act: -0.1700
Data Index: 5146741 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.5115. Min Act: -0.1700
Data Index: 1833513 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4802. Min Act: -0.1700
Data Index: 5120917 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4802. Min Act: -0.1700
Data Index: 749707 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4802. Min Act: -0.1700
Data Index: 2835236 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4490. Min Act: -0.1700
Data Index: 1830853 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4177. Min Act: -0.1700
Data Index: 3032171 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4280542 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.3865. Min Act: -0.1700
Data Index: 1399853 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8552. Min Range: -7.8552
Max Act: 7.3552. Min Act: -0.1700
Data Index: 6141459 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19