Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.7566. Min Act: -0.1700
Data Index: 6966593 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.4441. Min Act: -0.1700
Data Index: 4356854 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.4441. Min Act: -0.1700
Data Index: 456388 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.4754. Min Act: -0.1700
Data Index: 2137018 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.4441. Min Act: -0.1700
Data Index: 8023613 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.4129. Min Act: -0.1700
Data Index: 376880 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.3816. Min Act: -0.1700
Data Index: 3790756 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.3504. Min Act: -0.1700
Data Index: 7192725 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.3191. Min Act: -0.1700
Data Index: 6032437 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.3191. Min Act: -0.1700
Data Index: 8783123 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.3191. Min Act: -0.1700
Data Index: 8291232 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2566. Min Act: -0.1700
Data Index: 309046 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2254. Min Act: -0.1700
Data Index: 3351944 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2566. Min Act: -0.1700
Data Index: 7396021 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2254. Min Act: -0.1700
Data Index: 3136110 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2254. Min Act: -0.1700
Data Index: 1318716 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.2254. Min Act: -0.1700
Data Index: 7791854 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.1941. Min Act: -0.1700
Data Index: 7470902 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.1941. Min Act: -0.1700
Data Index: 129161 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7566. Min Range: -4.7566
Max Act: 4.1941. Min Act: -0.1700
Data Index: 4359629 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19