Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0865. Min Range: -1.0865
Max Act: 1.0865. Min Act: -0.1667
Data Index: 6793110 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9993. Min Act: -0.1689
Data Index: 2266178 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9820. Min Act: -0.1685
Data Index: 3595205 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9820. Min Act: -0.1700
Data Index: 8573517 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9993. Min Act: -0.1698
Data Index: 6831684 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9474. Min Act: -0.1700
Data Index: 3913518 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9647. Min Act: -0.1681
Data Index: 2579124 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9474. Min Act: -0.1690
Data Index: 4154767 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9474. Min Act: -0.1612
Data Index: 3804895 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9474. Min Act: -0.1697
Data Index: 184859 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9302. Min Act: -0.1699
Data Index: 2070947 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9474. Min Act: -0.1659
Data Index: 4450576 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9302. Min Act: -0.1700
Data Index: 2106033 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9302. Min Act: -0.1698
Data Index: 845835 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9302. Min Act: -0.1696
Data Index: 4988800 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9302. Min Act: -0.1699
Data Index: 7636624 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9216. Min Act: -0.1700
Data Index: 3224643 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9216. Min Act: -0.1695
Data Index: 4159070 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9216. Min Act: -0.1699
Data Index: 1200800 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0865. Min Range: -1.0865
Max Act: 0.9130. Min Act: -0.1700
Data Index: 3978184 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19