Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4627 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.8469. Min Act: -0.1700
Data Index: 3019971 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.6281. Min Act: -0.1700
Data Index: 218121 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.5969. Min Act: -0.1700
Data Index: 2216065 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.5344. Min Act: -0.1700
Data Index: 8638812 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.5031. Min Act: -0.1700
Data Index: 2851880 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.4719. Min Act: -0.1700
Data Index: 7773094 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.4094. Min Act: -0.1700
Data Index: 4117867 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.3469. Min Act: -0.1700
Data Index: 4282547 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.3156. Min Act: -0.1700
Data Index: 5222259 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2531. Min Act: -0.1700
Data Index: 4298958 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2844. Min Act: -0.1700
Data Index: 1308276 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2531. Min Act: -0.1700
Data Index: 2581977 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2844. Min Act: -0.1700
Data Index: 846477 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2531. Min Act: -0.1700
Data Index: 762881 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.2219. Min Act: -0.1700
Data Index: 6960150 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.1906. Min Act: -0.1700
Data Index: 1986268 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.1594. Min Act: -0.1700
Data Index: 4034678 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.1594. Min Act: -0.1700
Data Index: 8615409 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.1281. Min Act: -0.1700
Data Index: 3246694 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8469. Min Range: -7.8469
Max Act: 7.1594. Min Act: -0.1700
Data Index: 605616 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19