Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3754 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1165. Min Range: -7.1165
Max Act: 7.1165. Min Act: -0.1700
Data Index: 3134600 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.9602. Min Act: -0.1700
Data Index: 2145491 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.9602. Min Act: -0.1700
Data Index: 8792025 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.9290. Min Act: -0.1700
Data Index: 2440294 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.8665. Min Act: -0.1700
Data Index: 5026517 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.8352. Min Act: -0.1700
Data Index: 4822903 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.8352. Min Act: -0.1700
Data Index: 6616542 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.8040. Min Act: -0.1700
Data Index: 7049792 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.7727. Min Act: -0.1700
Data Index: 8135638 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6866496 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.7102. Min Act: -0.1700
Data Index: 7531557 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6790. Min Act: -0.1700
Data Index: 622006 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6790. Min Act: -0.1700
Data Index: 3049637 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6790. Min Act: -0.1700
Data Index: 1228779 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6790. Min Act: -0.1700
Data Index: 5489492 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6790. Min Act: -0.1700
Data Index: 5335534 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6477. Min Act: -0.1700
Data Index: 1943095 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6477. Min Act: -0.1700
Data Index: 8005838 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.6477. Min Act: -0.1700
Data Index: 5481942 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1165. Min Range: -7.1165
Max Act: 6.5852. Min Act: -0.1700
Data Index: 2368612 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19