Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 438 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0919. Min Range: -5.0919
Max Act: 5.0919. Min Act: -0.1700
Data Index: 8346098 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0919. Min Range: -5.0919
Max Act: 5.0294. Min Act: -0.1700
Data Index: 1164072 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9981. Min Act: -0.1700
Data Index: 1164073 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2826822 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 4758693 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8731. Min Act: -0.1700
Data Index: 4484040 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8419. Min Act: -0.1700
Data Index: 3495026 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8106. Min Act: -0.1700
Data Index: 4578336 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7794. Min Act: -0.1700
Data Index: 942802 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.8106. Min Act: -0.1700
Data Index: 260790 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7794. Min Act: -0.1700
Data Index: 2143161 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7794. Min Act: -0.1700
Data Index: 182786 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5080268 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7481. Min Act: -0.1700
Data Index: 4542087 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7169. Min Act: -0.1700
Data Index: 4660062 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7169. Min Act: -0.1700
Data Index: 2596362 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.7169. Min Act: -0.1700
Data Index: 4242589 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.6856. Min Act: -0.1700
Data Index: 2223414 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1330373 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0919. Min Range: -5.0919
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1050128 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19