Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2397 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.6493. Min Act: -0.1700
Data Index: 1378272 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.5556. Min Act: -0.1700
Data Index: 8436320 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.5243. Min Act: -0.1700
Data Index: 7977902 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.4931. Min Act: -0.1700
Data Index: 6063820 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.4618. Min Act: -0.1700
Data Index: 7977899 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3993. Min Act: -0.1700
Data Index: 8688848 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3993. Min Act: -0.1700
Data Index: 1079492 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3993. Min Act: -0.1700
Data Index: 178850 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3681. Min Act: -0.1700
Data Index: 3584373 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3681. Min Act: -0.1700
Data Index: 2090560 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8684206 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3368. Min Act: -0.1700
Data Index: 1845826 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3056. Min Act: -0.1700
Data Index: 655749 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.3056. Min Act: -0.1700
Data Index: 7563762 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2743. Min Act: -0.1700
Data Index: 7326589 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2743. Min Act: -0.1700
Data Index: 6063818 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2743. Min Act: -0.1700
Data Index: 6385597 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2431. Min Act: -0.1700
Data Index: 467973 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2431. Min Act: -0.1700
Data Index: 328700 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6493. Min Range: -5.6493
Max Act: 5.2431. Min Act: -0.1700
Data Index: 3415355 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19