Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.8001. Min Act: -0.1700
Data Index: 1204124 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7918. Min Act: -0.1699
Data Index: 7716578 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7918. Min Act: -0.1700
Data Index: 484693 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7834. Min Act: -0.1699
Data Index: 4248796 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7751. Min Act: -0.1700
Data Index: 7118344 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7751. Min Act: -0.1700
Data Index: 3705110 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7667. Min Act: -0.1700
Data Index: 7105422 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7501. Min Act: -0.1700
Data Index: 7799602 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7336. Min Act: -0.1691
Data Index: 4473996 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7254. Min Act: -0.1697
Data Index: 5681935 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7336. Min Act: -0.1689
Data Index: 7621388 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7172. Min Act: -0.1700
Data Index: 4489992 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7254. Min Act: -0.1700
Data Index: 1785248 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7090. Min Act: -0.1700
Data Index: 1204141 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7090. Min Act: -0.1699
Data Index: 3432801 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7172. Min Act: -0.1700
Data Index: 4203752 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7008. Min Act: -0.1700
Data Index: 7471941 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.6927. Min Act: -0.1700
Data Index: 1170267 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.6927. Min Act: -0.1700
Data Index: 2376890 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8001. Min Range: -0.8001
Max Act: 0.7090. Min Act: -0.1700
Data Index: 2504586 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19