Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.7208. Min Act: -0.1700
Data Index: 2231145 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5958. Min Act: -0.1700
Data Index: 5257926 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5333. Min Act: -0.1700
Data Index: 4680962 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5333. Min Act: -0.1700
Data Index: 7395316 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5020. Min Act: -0.1700
Data Index: 2606109 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5020. Min Act: -0.1700
Data Index: 8258225 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5020. Min Act: -0.1700
Data Index: 4745178 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.5020. Min Act: -0.1700
Data Index: 463369 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 28453 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 2863661 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 5673004 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 8113605 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 4626672 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 2252789 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4708. Min Act: -0.1700
Data Index: 4057813 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4395. Min Act: -0.1700
Data Index: 53528 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3142295 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4395. Min Act: -0.1700
Data Index: 3809258 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6248432 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7208. Min Range: -4.7208
Max Act: 4.4082. Min Act: -0.1700
Data Index: 3083759 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19