Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0519. Min Range: -11.0519
Max Act: 11.0519. Min Act: -0.1700
Data Index: 5924652 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0519. Min Range: -11.0519
Max Act: 10.3644. Min Act: -0.1700
Data Index: 3025166 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.9894. Min Act: -0.1700
Data Index: 7827165 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.7394. Min Act: -0.1700
Data Index: 6464102 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.7394. Min Act: -0.1700
Data Index: 8086433 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6769. Min Act: -0.1700
Data Index: 4581260 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6769. Min Act: -0.1700
Data Index: 3213617 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6769. Min Act: -0.1700
Data Index: 6518640 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6769. Min Act: -0.1700
Data Index: 3560761 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6144. Min Act: -0.1700
Data Index: 1350871 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 1212970 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.6144. Min Act: -0.1700
Data Index: 1439569 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 2582706 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 4560714 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 3410279 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 6353433 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.5519. Min Act: -0.1700
Data Index: 7741544 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.4894. Min Act: -0.1700
Data Index: 4353275 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.4894. Min Act: -0.1700
Data Index: 3704003 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0519. Min Range: -11.0519
Max Act: 9.4894. Min Act: -0.1700
Data Index: 5959415 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19