Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5399 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.2371. Min Act: -0.1700
Data Index: 4377172 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.2371. Min Act: -0.1700
Data Index: 953677 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1746. Min Act: -0.1700
Data Index: 149494 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.2059. Min Act: -0.1700
Data Index: 7393163 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1434. Min Act: -0.1700
Data Index: 490657 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1434. Min Act: -0.1700
Data Index: 2473179 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.1121. Min Act: -0.1700
Data Index: 3517794 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0809. Min Act: -0.1700
Data Index: 3002436 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0496. Min Act: -0.1700
Data Index: 557889 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2371. Min Range: -7.2371
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3223616 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9559. Min Act: -0.1700
Data Index: 3779088 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.9246. Min Act: -0.1700
Data Index: 3887338 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8934. Min Act: -0.1700
Data Index: 4839227 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8621. Min Act: -0.1700
Data Index: 8820232 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8934. Min Act: -0.1700
Data Index: 8370068 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8621. Min Act: -0.1700
Data Index: 3517796 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8309. Min Act: -0.1700
Data Index: 5479570 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8309. Min Act: -0.1700
Data Index: 4966396 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.8309. Min Act: -0.1700
Data Index: 8122267 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2371. Min Range: -7.2371
Max Act: 6.7996. Min Act: -0.1700
Data Index: 8323356 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19