Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.8848. Min Act: -0.1700
Data Index: 7918786 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.8223. Min Act: -0.1700
Data Index: 4469508 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.7285. Min Act: -0.1700
Data Index: 6158088 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6973. Min Act: -0.1700
Data Index: 3356344 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6973. Min Act: -0.1700
Data Index: 1348101 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6660. Min Act: -0.1700
Data Index: 8001805 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.7285. Min Act: -0.1700
Data Index: 7098851 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6660. Min Act: -0.1700
Data Index: 5710204 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6973. Min Act: -0.1700
Data Index: 777825 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6660. Min Act: -0.1700
Data Index: 2790683 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6660. Min Act: -0.1700
Data Index: 2131175 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6348. Min Act: -0.1700
Data Index: 7644255 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6660. Min Act: -0.1700
Data Index: 4677268 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6035. Min Act: -0.1700
Data Index: 7055199 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6035. Min Act: -0.1700
Data Index: 4936892 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.6035. Min Act: -0.1700
Data Index: 4730412 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.5723. Min Act: -0.1700
Data Index: 3746051 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.5410. Min Act: -0.1700
Data Index: 7045440 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.5723. Min Act: -0.1700
Data Index: 6154099 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8848. Min Range: -5.8848
Max Act: 5.5723. Min Act: -0.1700
Data Index: 2761649 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19