Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.2162. Min Act: -0.1700
Data Index: 5104977 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.1996. Min Act: -0.1698
Data Index: 6728357 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.1163. Min Act: -0.1700
Data Index: 3095265 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.1163. Min Act: -0.1684
Data Index: 483067 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.0324. Min Act: -0.1699
Data Index: 5031999 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2162. Min Range: -2.2162
Max Act: 2.0155. Min Act: -0.1680
Data Index: 869023 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9987. Min Act: -0.1700
Data Index: 1937808 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9817. Min Act: -0.1697
Data Index: 8471484 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9817. Min Act: -0.1699
Data Index: 642122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9478. Min Act: -0.1699
Data Index: 6623548 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9478. Min Act: -0.1700
Data Index: 4848213 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9648. Min Act: -0.1678
Data Index: 8519817 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9308. Min Act: -0.1700
Data Index: 2220305 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9308. Min Act: -0.1689
Data Index: 5258778 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.8968. Min Act: -0.1699
Data Index: 7024702 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9138. Min Act: -0.1696
Data Index: 6469415 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.9138. Min Act: -0.1700
Data Index: 2175193 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.8968. Min Act: -0.1694
Data Index: 5111557 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.8797. Min Act: -0.1700
Data Index: 739090 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2162. Min Range: -2.2162
Max Act: 1.8797. Min Act: -0.1700
Data Index: 7578371 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19