Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.8688. Min Act: -0.1700
Data Index: 2090326 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.7125. Min Act: -0.1700
Data Index: 4808521 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.6500. Min Act: -0.1700
Data Index: 3794132 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.5563. Min Act: -0.1700
Data Index: 3751426 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.5563. Min Act: -0.1700
Data Index: 6871183 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.4938. Min Act: -0.1700
Data Index: 7561105 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.4000. Min Act: -0.1700
Data Index: 4388532 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.3688. Min Act: -0.1700
Data Index: 6092927 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.3375. Min Act: -0.1700
Data Index: 4127486 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.3375. Min Act: -0.1700
Data Index: 3979265 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.3063. Min Act: -0.1700
Data Index: 4481947 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.2438. Min Act: -0.1700
Data Index: 6136493 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.2438. Min Act: -0.1700
Data Index: 2757554 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.2438. Min Act: -0.1700
Data Index: 2015939 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.2125. Min Act: -0.1700
Data Index: 2305721 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.1813. Min Act: -0.1700
Data Index: 498172 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.1813. Min Act: -0.1700
Data Index: 1850819 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.1813. Min Act: -0.1700
Data Index: 1064406 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.1813. Min Act: -0.1700
Data Index: 8150363 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8688. Min Range: -6.8688
Max Act: 6.1500. Min Act: -0.1700
Data Index: 7313223 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19