Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.4237. Min Act: -0.1700
Data Index: 7832202 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.2987. Min Act: -0.1700
Data Index: 4576971 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.2362. Min Act: -0.1700
Data Index: 1081416 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.2362. Min Act: -0.1700
Data Index: 444844 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.2362. Min Act: -0.1700
Data Index: 3348378 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.2362. Min Act: -0.1700
Data Index: 1201104 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1737. Min Act: -0.1700
Data Index: 5341940 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1737. Min Act: -0.1700
Data Index: 4493182 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1737. Min Act: -0.1700
Data Index: 8383363 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1112. Min Act: -0.1700
Data Index: 8460263 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1112. Min Act: -0.1700
Data Index: 4768986 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1112. Min Act: -0.1700
Data Index: 1769769 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.1112. Min Act: -0.1700
Data Index: 330101 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 1882016 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 7659147 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 2576726 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 3071517 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 6884688 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 910173 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4237. Min Range: -8.4237
Max Act: 8.0487. Min Act: -0.1700
Data Index: 6105904 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19