Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3328 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.2988. Min Act: -0.1700
Data Index: 3384697 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.2676. Min Act: -0.1700
Data Index: 2231664 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.2363. Min Act: -0.1700
Data Index: 783107 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.2363. Min Act: -0.1700
Data Index: 7939774 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.1426. Min Act: -0.1700
Data Index: 1434692 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.1738. Min Act: -0.1700
Data Index: 6792508 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.1113. Min Act: -0.1700
Data Index: 7229300 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.0801. Min Act: -0.1700
Data Index: 1231334 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.0488. Min Act: -0.1700
Data Index: 7224642 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.0488. Min Act: -0.1700
Data Index: 5553095 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2988. Min Range: -7.2988
Max Act: 7.0176. Min Act: -0.1700
Data Index: 1808676 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9551. Min Act: -0.1700
Data Index: 8094710 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9551. Min Act: -0.1700
Data Index: 6066715 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9863. Min Act: -0.1700
Data Index: 4431600 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9238. Min Act: -0.1700
Data Index: 2585182 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9238. Min Act: -0.1700
Data Index: 2542398 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9238. Min Act: -0.1700
Data Index: 5390049 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.9238. Min Act: -0.1700
Data Index: 3394072 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.8926. Min Act: -0.1700
Data Index: 3617946 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2988. Min Range: -7.2988
Max Act: 6.8926. Min Act: -0.1700
Data Index: 1053811 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19