Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.1099. Min Act: -0.1700
Data Index: 3850699 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.1257. Min Act: -0.1700
Data Index: 435750 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0784. Min Act: -0.1700
Data Index: 3348379 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0784. Min Act: -0.1700
Data Index: 4572907 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0784. Min Act: -0.1700
Data Index: 32370 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0626. Min Act: -0.1700
Data Index: 4347854 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0626. Min Act: -0.1700
Data Index: 6582968 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0468. Min Act: -0.1700
Data Index: 6664227 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0468. Min Act: -0.1700
Data Index: 7067896 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0468. Min Act: -0.1700
Data Index: 2623087 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0468. Min Act: -0.1700
Data Index: 1275349 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0311. Min Act: -0.1700
Data Index: 2761554 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0311. Min Act: -0.1700
Data Index: 6643119 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0153. Min Act: -0.1700
Data Index: 3785713 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1257. Min Range: -3.1257
Max Act: 3.0153. Min Act: -0.1700
Data Index: 115756 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1257. Min Range: -3.1257
Max Act: 2.9995. Min Act: -0.1700
Data Index: 7361526 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1257. Min Range: -3.1257
Max Act: 2.9995. Min Act: -0.1700
Data Index: 2561947 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1257. Min Range: -3.1257
Max Act: 2.9995. Min Act: -0.1700
Data Index: 3460817 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1257. Min Range: -3.1257
Max Act: 2.9995. Min Act: -0.1700
Data Index: 3171291 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1257. Min Range: -3.1257
Max Act: 2.9836. Min Act: -0.1700
Data Index: 4273234 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19