Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3926. Min Range: -6.3926
Max Act: 6.3926. Min Act: -0.1700
Data Index: 454741 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3926. Min Range: -6.3926
Max Act: 6.2364. Min Act: -0.1700
Data Index: 7782244 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3926. Min Range: -6.3926
Max Act: 6.1426. Min Act: -0.1700
Data Index: 4090698 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3926. Min Range: -6.3926
Max Act: 6.0176. Min Act: -0.1700
Data Index: 8094075 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.9551. Min Act: -0.1700
Data Index: 2809069 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8200673 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.9239. Min Act: -0.1700
Data Index: 7334277 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6473021 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.9239. Min Act: -0.1700
Data Index: 2582351 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 3722322 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 8109549 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8614. Min Act: -0.1700
Data Index: 1783192 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 4018730 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 369184 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8614. Min Act: -0.1700
Data Index: 1749623 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8614. Min Act: -0.1700
Data Index: 3661286 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8301. Min Act: -0.1700
Data Index: 6529618 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.8301. Min Act: -0.1700
Data Index: 518289 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.7989. Min Act: -0.1700
Data Index: 3073907 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3926. Min Range: -6.3926
Max Act: 5.7989. Min Act: -0.1700
Data Index: 3465382 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19