Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4977 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1465. Min Act: -0.1700
Data Index: 7926107 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0834. Min Act: -0.1700
Data Index: 3287011 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0519. Min Act: -0.1700
Data Index: 1870630 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0045. Min Act: -0.1700
Data Index: 7743866 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9729. Min Act: -0.1700
Data Index: 931915 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9571. Min Act: -0.1700
Data Index: 8334788 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9571. Min Act: -0.1700
Data Index: 8607880 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 4530982 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 6208596 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 1264317 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 5128450 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9096. Min Act: -0.1700
Data Index: 662173 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9096. Min Act: -0.1700
Data Index: 3479370 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 264706 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 1006508 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9096. Min Act: -0.1700
Data Index: 2060352 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 2279561 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 1622112 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8778. Min Act: -0.1700
Data Index: 447867 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8778. Min Act: -0.1700
Data Index: 5814314 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19