Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.6400. Min Act: -0.1700
Data Index: 3730958 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.6087. Min Act: -0.1700
Data Index: 5571757 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.5775. Min Act: -0.1700
Data Index: 4561811 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.5150. Min Act: -0.1700
Data Index: 2483864 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.5150. Min Act: -0.1700
Data Index: 230606 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.4837. Min Act: -0.1700
Data Index: 6985119 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.4525. Min Act: -0.1700
Data Index: 3537504 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.4212. Min Act: -0.1700
Data Index: 8586920 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.4212. Min Act: -0.1700
Data Index: 4335752 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.3900. Min Act: -0.1700
Data Index: 6099000 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.3900. Min Act: -0.1700
Data Index: 6279403 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.3900. Min Act: -0.1700
Data Index: 2460729 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2962. Min Act: -0.1700
Data Index: 360511 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2962. Min Act: -0.1700
Data Index: 2424644 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.3275. Min Act: -0.1700
Data Index: 3206925 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2962. Min Act: -0.1700
Data Index: 8670565 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2962. Min Act: -0.1700
Data Index: 3186705 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2650. Min Act: -0.1700
Data Index: 6341244 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2650. Min Act: -0.1700
Data Index: 7353873 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6400. Min Range: -6.6400
Max Act: 6.2025. Min Act: -0.1700
Data Index: 2848635 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19