Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5831 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2174. Min Range: -6.2174
Max Act: 6.2174. Min Act: -0.1700
Data Index: 899376 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2174. Min Range: -6.2174
Max Act: 6.0299. Min Act: -0.1700
Data Index: 7692229 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.8424. Min Act: -0.1700
Data Index: 6292066 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.7799. Min Act: -0.1700
Data Index: 8387209 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.7174. Min Act: -0.1700
Data Index: 7908172 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.7174. Min Act: -0.1700
Data Index: 3116317 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.7174. Min Act: -0.1700
Data Index: 4494574 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6549. Min Act: -0.1700
Data Index: 4905170 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8631837 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8095106 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8095105 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 7362436 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 8508099 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 829308 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 5485450 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 4193063 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.5924. Min Act: -0.1700
Data Index: 7723593 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.5924. Min Act: -0.1700
Data Index: 7377909 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.5924. Min Act: -0.1700
Data Index: 8095108 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2174. Min Range: -6.2174
Max Act: 5.5612. Min Act: -0.1700
Data Index: 609924 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19