Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3771 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0125. Min Range: -6.0125
Max Act: 6.0125. Min Act: -0.1700
Data Index: 2018330 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.9500. Min Act: -0.1700
Data Index: 4270271 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.8875. Min Act: -0.1700
Data Index: 4402541 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.8563. Min Act: -0.1700
Data Index: 4566258 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7938. Min Act: -0.1700
Data Index: 4019881 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7625. Min Act: -0.1700
Data Index: 4436220 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7625. Min Act: -0.1700
Data Index: 4428004 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7625. Min Act: -0.1700
Data Index: 6492877 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7625. Min Act: -0.1700
Data Index: 6656375 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7625. Min Act: -0.1700
Data Index: 7405543 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7938. Min Act: -0.1700
Data Index: 114414 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 5000423 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 7881085 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 4792758 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 3631177 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7313. Min Act: -0.1700
Data Index: 5689522 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7000. Min Act: -0.1700
Data Index: 3640699 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.6375. Min Act: -0.1700
Data Index: 222619 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.7000. Min Act: -0.1700
Data Index: 6416515 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0125. Min Range: -6.0125
Max Act: 5.6688. Min Act: -0.1700
Data Index: 7634067 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19