Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0270. Min Range: -5.0270
Max Act: 5.0270. Min Act: -0.1700
Data Index: 4869135 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.9020. Min Act: -0.1700
Data Index: 769793 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.8708. Min Act: -0.1700
Data Index: 1619033 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.8708. Min Act: -0.1700
Data Index: 3402434 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7770. Min Act: -0.1700
Data Index: 681937 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7458. Min Act: -0.1700
Data Index: 5671778 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7458. Min Act: -0.1700
Data Index: 1589693 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7770. Min Act: -0.1700
Data Index: 7336664 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7458. Min Act: -0.1700
Data Index: 1538422 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7458. Min Act: -0.1700
Data Index: 8553910 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7145. Min Act: -0.1700
Data Index: 7840087 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.7145. Min Act: -0.1700
Data Index: 2652669 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 46209 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 4712319 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 858881 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 5361592 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 7510552 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6833. Min Act: -0.1700
Data Index: 4458516 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6520. Min Act: -0.1700
Data Index: 1563429 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0270. Min Range: -5.0270
Max Act: 4.6208. Min Act: -0.1700
Data Index: 3410569 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19