Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.3700. Min Act: -0.1700
Data Index: 3153145 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.2762. Min Act: -0.1700
Data Index: 5568193 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.3075. Min Act: -0.1700
Data Index: 6233256 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.2450. Min Act: -0.1700
Data Index: 8815289 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.2137. Min Act: -0.1700
Data Index: 253756 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.2137. Min Act: -0.1700
Data Index: 7742734 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1512. Min Act: -0.1700
Data Index: 5530875 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1512. Min Act: -0.1700
Data Index: 780857 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1825. Min Act: -0.1700
Data Index: 795024 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1825. Min Act: -0.1700
Data Index: 5948040 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1512. Min Act: -0.1700
Data Index: 1898447 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1825. Min Act: -0.1700
Data Index: 7493679 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1512. Min Act: -0.1700
Data Index: 4834746 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1512. Min Act: -0.1700
Data Index: 483986 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1200. Min Act: -0.1700
Data Index: 6255195 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1200. Min Act: -0.1700
Data Index: 4932552 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1200. Min Act: -0.1700
Data Index: 3294077 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1200. Min Act: -0.1700
Data Index: 8694429 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.1200. Min Act: -0.1700
Data Index: 1886525 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3700. Min Range: -6.3700
Max Act: 6.0887. Min Act: -0.1700
Data Index: 3513038 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19