Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5336 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.7475. Min Act: -0.1700
Data Index: 2967513 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.6850. Min Act: -0.1700
Data Index: 111987 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.6537. Min Act: -0.1700
Data Index: 6802558 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.6225. Min Act: -0.1700
Data Index: 4226586 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.5912. Min Act: -0.1700
Data Index: 6959716 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1507053 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.5287. Min Act: -0.1700
Data Index: 6995568 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.5287. Min Act: -0.1700
Data Index: 5950988 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4662. Min Act: -0.1700
Data Index: 7761465 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4662. Min Act: -0.1700
Data Index: 6397376 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2154585 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4037. Min Act: -0.1700
Data Index: 7710736 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4037. Min Act: -0.1700
Data Index: 4985990 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4350. Min Act: -0.1700
Data Index: 719034 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.4037. Min Act: -0.1700
Data Index: 8759309 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.3725. Min Act: -0.1700
Data Index: 6115696 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7580308 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.3725. Min Act: -0.1700
Data Index: 5558972 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.3725. Min Act: -0.1700
Data Index: 7253862 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7475. Min Range: -5.7475
Max Act: 5.3725. Min Act: -0.1700
Data Index: 3052038 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19