Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5876 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.7502. Min Act: -0.1700
Data Index: 1440454 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.6252. Min Act: -0.1700
Data Index: 2353154 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.6565. Min Act: -0.1700
Data Index: 5789919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.6252. Min Act: -0.1700
Data Index: 4655570 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.6252. Min Act: -0.1700
Data Index: 5694731 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.5627. Min Act: -0.1700
Data Index: 7209384 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.5627. Min Act: -0.1700
Data Index: 7371204 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.5315. Min Act: -0.1700
Data Index: 6911477 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4377. Min Act: -0.1700
Data Index: 8070578 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4377. Min Act: -0.1700
Data Index: 3952490 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4377. Min Act: -0.1700
Data Index: 294310 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4377. Min Act: -0.1700
Data Index: 3601308 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4065. Min Act: -0.1700
Data Index: 4458097 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4065. Min Act: -0.1700
Data Index: 7238902 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.3752. Min Act: -0.1700
Data Index: 1026394 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.3752. Min Act: -0.1700
Data Index: 5456986 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.3752. Min Act: -0.1699
Data Index: 2152670 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.4065. Min Act: -0.1677
Data Index: 4619513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.3440. Min Act: -0.1700
Data Index: 555115 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7502. Min Range: -4.7502
Max Act: 4.3440. Min Act: -0.1700
Data Index: 3405507 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19