Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1951 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1002. Min Range: -4.1002
Max Act: 4.1002. Min Act: -0.1700
Data Index: 4816410 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7563. Min Act: -0.1700
Data Index: 647634 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7876. Min Act: -0.1700
Data Index: 6445928 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.8189. Min Act: -0.1700
Data Index: 2036431 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7876. Min Act: -0.1700
Data Index: 4347123 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7876. Min Act: -0.1700
Data Index: 3468946 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7876. Min Act: -0.1700
Data Index: 5043799 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7563. Min Act: -0.1700
Data Index: 7240863 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7250. Min Act: -0.1700
Data Index: 2509722 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7250. Min Act: -0.1700
Data Index: 5478399 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.7250. Min Act: -0.1700
Data Index: 4687343 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 1344439 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 5428021 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 8663880 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 7666111 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 7890805 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6937. Min Act: -0.1700
Data Index: 2867648 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6625. Min Act: -0.1700
Data Index: 1359213 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6312. Min Act: -0.1700
Data Index: 7957123 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1002. Min Range: -4.1002
Max Act: 3.6625. Min Act: -0.1700
Data Index: 995106 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19