Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6062 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.2058. Min Act: -0.1700
Data Index: 6800287 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.2058. Min Act: -0.1700
Data Index: 6958175 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.1433. Min Act: -0.1700
Data Index: 6666868 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.1433. Min Act: -0.1700
Data Index: 5207508 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.1433. Min Act: -0.1700
Data Index: 5895416 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2058. Min Range: -8.2058
Max Act: 8.0808. Min Act: -0.1700
Data Index: 6882633 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.9558. Min Act: -0.1700
Data Index: 4974024 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.9558. Min Act: -0.1700
Data Index: 5571903 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.8933. Min Act: -0.1700
Data Index: 2537485 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.8933. Min Act: -0.1700
Data Index: 1519523 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.8308. Min Act: -0.1700
Data Index: 8498594 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7683. Min Act: -0.1700
Data Index: 3532558 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7683. Min Act: -0.1700
Data Index: 5395189 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7683. Min Act: -0.1700
Data Index: 1761025 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7683. Min Act: -0.1700
Data Index: 3285894 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 6045402 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7683. Min Act: -0.1700
Data Index: 3971753 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 6859589 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 5630658 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2058. Min Range: -8.2058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 4151426 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19