Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3621. Min Range: -6.3621
Max Act: 6.3621. Min Act: -0.1700
Data Index: 2392704 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.9871. Min Act: -0.1700
Data Index: 1090721 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.9871. Min Act: -0.1700
Data Index: 124245 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.9559. Min Act: -0.1700
Data Index: 996504 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.9559. Min Act: -0.1700
Data Index: 894893 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.9246. Min Act: -0.1700
Data Index: 8490763 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8934. Min Act: -0.1700
Data Index: 8823233 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8621. Min Act: -0.1700
Data Index: 2326760 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8621. Min Act: -0.1700
Data Index: 3206533 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 8041886 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 8725494 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 4436545 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 1329388 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 4239746 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.8309. Min Act: -0.1700
Data Index: 4765156 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.7996. Min Act: -0.1700
Data Index: 2544357 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4553694 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.7684. Min Act: -0.1700
Data Index: 4807431 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.7684. Min Act: -0.1700
Data Index: 5851791 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3621. Min Range: -6.3621
Max Act: 5.7684. Min Act: -0.1700
Data Index: 3732593 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19