Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1051 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1447. Min Range: -8.1447
Max Act: 8.1447. Min Act: -0.1700
Data Index: 2729933 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.9884. Min Act: -0.1700
Data Index: 7071348 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.8634. Min Act: -0.1700
Data Index: 3661490 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.6134. Min Act: -0.1700
Data Index: 6668629 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.5822. Min Act: -0.1700
Data Index: 6237843 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4884. Min Act: -0.1700
Data Index: 4270809 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4572. Min Act: -0.1700
Data Index: 549689 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4259. Min Act: -0.1700
Data Index: 4488935 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.4259. Min Act: -0.1700
Data Index: 4393621 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.3947. Min Act: -0.1700
Data Index: 4442786 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.3634. Min Act: -0.1700
Data Index: 8128527 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.3322. Min Act: -0.1700
Data Index: 971009 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.3009. Min Act: -0.1700
Data Index: 7657942 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.2384. Min Act: -0.1700
Data Index: 5491082 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.2384. Min Act: -0.1700
Data Index: 4908316 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.1759. Min Act: -0.1700
Data Index: 7482165 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.1759. Min Act: -0.1700
Data Index: 1826464 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.1447. Min Act: -0.1700
Data Index: 4103686 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.1447. Min Act: -0.1700
Data Index: 2725167 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1447. Min Range: -8.1447
Max Act: 7.1134. Min Act: -0.1700
Data Index: 42887 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19