Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1125. Min Range: -5.1125
Max Act: 5.1125. Min Act: -0.1700
Data Index: 7179864 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.9563. Min Act: -0.1700
Data Index: 6231599 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.9250. Min Act: -0.1700
Data Index: 5045187 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8938. Min Act: -0.1700
Data Index: 5072582 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8625. Min Act: -0.1700
Data Index: 7247777 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8625. Min Act: -0.1700
Data Index: 4754376 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8625. Min Act: -0.1700
Data Index: 8278660 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8000. Min Act: -0.1700
Data Index: 8652242 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2096320 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7688. Min Act: -0.1700
Data Index: 8279119 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8000. Min Act: -0.1700
Data Index: 3459077 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8000. Min Act: -0.1700
Data Index: 3293450 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8000. Min Act: -0.1700
Data Index: 3117584 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7375. Min Act: -0.1700
Data Index: 502790 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7688. Min Act: -0.1700
Data Index: 5531393 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.8000. Min Act: -0.1700
Data Index: 5082294 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7375. Min Act: -0.1700
Data Index: 7314716 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7375. Min Act: -0.1700
Data Index: 682976 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7375. Min Act: -0.1700
Data Index: 901276 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1125. Min Range: -5.1125
Max Act: 4.7375. Min Act: -0.1700
Data Index: 504441 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19