Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5409 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.2962. Min Act: -0.1700
Data Index: 1104695 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.2649. Min Act: -0.1700
Data Index: 712605 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.2024. Min Act: -0.1700
Data Index: 8677364 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.2024. Min Act: -0.1700
Data Index: 8809546 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.1712. Min Act: -0.1700
Data Index: 148514 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2962. Min Range: -7.2962
Max Act: 7.0774. Min Act: -0.1700
Data Index: 3247604 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.9524. Min Act: -0.1700
Data Index: 1520454 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.9212. Min Act: -0.1700
Data Index: 2869636 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.9212. Min Act: -0.1700
Data Index: 1941095 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.9212. Min Act: -0.1700
Data Index: 8373427 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.9212. Min Act: -0.1700
Data Index: 3650691 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8587. Min Act: -0.1700
Data Index: 3514020 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8587. Min Act: -0.1700
Data Index: 4012908 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8587. Min Act: -0.1700
Data Index: 2854042 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8587. Min Act: -0.1700
Data Index: 4847427 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8587. Min Act: -0.1700
Data Index: 8255056 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8274. Min Act: -0.1700
Data Index: 4847425 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8274. Min Act: -0.1700
Data Index: 5801503 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.8274. Min Act: -0.1700
Data Index: 3604097 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2962. Min Range: -7.2962
Max Act: 6.7962. Min Act: -0.1700
Data Index: 7252442 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19