Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.2340. Min Act: -0.1700
Data Index: 2706896 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.2652. Min Act: -0.1700
Data Index: 8801984 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.2027. Min Act: -0.1700
Data Index: 6124043 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8699610 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.1715. Min Act: -0.1700
Data Index: 7290003 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.1402. Min Act: -0.1698
Data Index: 7908377 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.1090. Min Act: -0.1700
Data Index: 4123051 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.1090. Min Act: -0.1700
Data Index: 8568464 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.0465. Min Act: -0.1699
Data Index: 7908369 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.0465. Min Act: -0.1700
Data Index: 3642669 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.0465. Min Act: -0.1700
Data Index: 3824194 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2652. Min Range: -6.2652
Max Act: 6.0465. Min Act: -0.1700
Data Index: 1288745 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9840. Min Act: -0.1700
Data Index: 8653712 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9527. Min Act: -0.1700
Data Index: 3185008 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9527. Min Act: -0.1700
Data Index: 6378726 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9527. Min Act: -0.1700
Data Index: 6427792 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9527. Min Act: -0.1700
Data Index: 7219790 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9215. Min Act: -0.1700
Data Index: 2272812 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.8902. Min Act: -0.1700
Data Index: 452535 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2652. Min Range: -6.2652
Max Act: 5.9215. Min Act: -0.1700
Data Index: 8654967 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19