Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.3933. Min Act: -0.1700
Data Index: 4962818 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.3308. Min Act: -0.1700
Data Index: 8626077 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.2058. Min Act: -0.1700
Data Index: 8534874 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.2370. Min Act: -0.1700
Data Index: 1726292 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.1433. Min Act: -0.1700
Data Index: 1880039 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.0808. Min Act: -0.1700
Data Index: 1486153 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.1120. Min Act: -0.1700
Data Index: 4271457 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.0808. Min Act: -0.1700
Data Index: 3757485 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3933. Min Range: -8.3933
Max Act: 8.0183. Min Act: -0.1700
Data Index: 4387945 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.9558. Min Act: -0.1700
Data Index: 7932612 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.9558. Min Act: -0.1700
Data Index: 5831146 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.9558. Min Act: -0.1700
Data Index: 202439 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.8933. Min Act: -0.1700
Data Index: 653583 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.9245. Min Act: -0.1700
Data Index: 2362194 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.8620. Min Act: -0.1700
Data Index: 4376393 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.8308. Min Act: -0.1700
Data Index: 2463410 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.8620. Min Act: -0.1700
Data Index: 7290659 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.8308. Min Act: -0.1700
Data Index: 758990 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.7058. Min Act: -0.1700
Data Index: 2857089 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3933. Min Range: -8.3933
Max Act: 7.6745. Min Act: -0.1700
Data Index: 3789463 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19