Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1266. Min Range: -5.1266
Max Act: 5.1266. Min Act: -0.1700
Data Index: 557755 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1266. Min Range: -5.1266
Max Act: 5.0329. Min Act: -0.1700
Data Index: 525500 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.9079. Min Act: -0.1700
Data Index: 4550024 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.8141. Min Act: -0.1700
Data Index: 8795872 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.7829. Min Act: -0.1700
Data Index: 4010543 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.7829. Min Act: -0.1700
Data Index: 6744668 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.7204. Min Act: -0.1700
Data Index: 2883190 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.7204. Min Act: -0.1700
Data Index: 4543383 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.6266. Min Act: -0.1700
Data Index: 7509546 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.6266. Min Act: -0.1700
Data Index: 3836367 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.6266. Min Act: -0.1700
Data Index: 924709 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.6266. Min Act: -0.1700
Data Index: 7794205 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5954. Min Act: -0.1700
Data Index: 3106858 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5641. Min Act: -0.1700
Data Index: 8427849 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5641. Min Act: -0.1700
Data Index: 2907075 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5641. Min Act: -0.1700
Data Index: 8129815 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5641. Min Act: -0.1700
Data Index: 2824612 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5329. Min Act: -0.1700
Data Index: 1771171 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5016. Min Act: -0.1700
Data Index: 5799565 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1266. Min Range: -5.1266
Max Act: 4.5016. Min Act: -0.1700
Data Index: 7082506 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19