Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.6512. Min Act: -0.1700
Data Index: 7887415 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2762. Min Act: -0.1700
Data Index: 7412575 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2762. Min Act: -0.1700
Data Index: 4600654 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2137. Min Act: -0.1700
Data Index: 41330 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2449. Min Act: -0.1700
Data Index: 617689 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2137. Min Act: -0.1700
Data Index: 739030 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.2137. Min Act: -0.1700
Data Index: 8642465 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1824. Min Act: -0.1700
Data Index: 4081954 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1824. Min Act: -0.1700
Data Index: 3354175 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1512. Min Act: -0.1700
Data Index: 2129444 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1512. Min Act: -0.1700
Data Index: 535701 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1199. Min Act: -0.1700
Data Index: 8241261 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1199. Min Act: -0.1700
Data Index: 5541247 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1199. Min Act: -0.1700
Data Index: 3820051 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.1199. Min Act: -0.1700
Data Index: 1363716 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.0886. Min Act: -0.1700
Data Index: 3040586 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.0886. Min Act: -0.1700
Data Index: 357153 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.0574. Min Act: -0.1700
Data Index: 3722331 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.0886. Min Act: -0.1700
Data Index: 3277304 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6512. Min Range: -4.6512
Max Act: 4.0886. Min Act: -0.1700
Data Index: 5817238 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19