Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.3781. Min Act: -0.1694
Data Index: 3716699 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.3252. Min Act: -0.1688
Data Index: 4828452 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2899. Min Act: -0.1684
Data Index: 2865973 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2899. Min Act: -0.1700
Data Index: 6372401 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2723. Min Act: -0.1700
Data Index: 5608697 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2899. Min Act: -0.1700
Data Index: 4193481 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2547. Min Act: -0.1694
Data Index: 2983597 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2194. Min Act: -0.1700
Data Index: 2957694 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1698
Data Index: 618560 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2194. Min Act: -0.1700
Data Index: 427649 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1699
Data Index: 5784386 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2194. Min Act: -0.1673
Data Index: 5656490 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1699
Data Index: 7029897 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1700
Data Index: 3668854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1687
Data Index: 8619200 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1576
Data Index: 6822398 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.2018. Min Act: -0.1699
Data Index: 6984272 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.1842. Min Act: -0.1627
Data Index: 3329772 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.1666. Min Act: -0.1700
Data Index: 8066337 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3781. Min Range: -1.3781
Max Act: 1.1490. Min Act: -0.1700
Data Index: 6420223 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19