Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.5526. Min Act: -0.1700
Data Index: 4382176 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.4901. Min Act: -0.1700
Data Index: 1072772 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.4588. Min Act: -0.1700
Data Index: 4644455 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.4276. Min Act: -0.1700
Data Index: 8777079 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3963. Min Act: -0.1700
Data Index: 983992 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3963. Min Act: -0.1700
Data Index: 2731921 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.4276. Min Act: -0.1700
Data Index: 481449 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3963. Min Act: -0.1700
Data Index: 7945511 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3338. Min Act: -0.1700
Data Index: 1915565 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3651. Min Act: -0.1700
Data Index: 5581355 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3338. Min Act: -0.1700
Data Index: 1694532 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3338. Min Act: -0.1700
Data Index: 8262331 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.3026. Min Act: -0.1700
Data Index: 8759275 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2713. Min Act: -0.1700
Data Index: 6377120 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2713. Min Act: -0.1700
Data Index: 916167 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2401. Min Act: -0.1700
Data Index: 4301440 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2088. Min Act: -0.1700
Data Index: 1524014 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2088. Min Act: -0.1700
Data Index: 2979219 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2088. Min Act: -0.1700
Data Index: 1409505 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5526. Min Range: -6.5526
Max Act: 6.2088. Min Act: -0.1700
Data Index: 2886977 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19