Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2535. Min Range: -8.2535
Max Act: 8.2535. Min Act: -0.1700
Data Index: 8612829 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2535. Min Range: -8.2535
Max Act: 8.1285. Min Act: -0.1700
Data Index: 2000293 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.9722. Min Act: -0.1700
Data Index: 4354091 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.9097. Min Act: -0.1700
Data Index: 1721903 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.7847. Min Act: -0.1700
Data Index: 3551621 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.7222. Min Act: -0.1700
Data Index: 4353650 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.7222. Min Act: -0.1700
Data Index: 6926036 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6910. Min Act: -0.1700
Data Index: 2183960 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.7222. Min Act: -0.1700
Data Index: 3641580 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6597. Min Act: -0.1700
Data Index: 5785080 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6910. Min Act: -0.1700
Data Index: 7496710 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6285. Min Act: -0.1700
Data Index: 628047 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5972. Min Act: -0.1700
Data Index: 2125237 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6597. Min Act: -0.1700
Data Index: 1157901 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.6285. Min Act: -0.1700
Data Index: 2414912 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5972. Min Act: -0.1700
Data Index: 6409297 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5660. Min Act: -0.1700
Data Index: 8245405 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5660. Min Act: -0.1700
Data Index: 3814597 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5347. Min Act: -0.1700
Data Index: 1877043 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2535. Min Range: -8.2535
Max Act: 7.5347. Min Act: -0.1700
Data Index: 33772 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19