Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4618 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4921. Min Range: -5.4921
Max Act: 5.4921. Min Act: -0.1700
Data Index: 2183301 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.9921. Min Act: -0.1700
Data Index: 8376786 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.9609. Min Act: -0.1700
Data Index: 8022576 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8984. Min Act: -0.1700
Data Index: 2543045 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8984. Min Act: -0.1700
Data Index: 605467 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8984. Min Act: -0.1700
Data Index: 4621925 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8671. Min Act: -0.1700
Data Index: 6585220 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8984. Min Act: -0.1700
Data Index: 2171843 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8671. Min Act: -0.1700
Data Index: 3986684 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8671. Min Act: -0.1700
Data Index: 8115405 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8671. Min Act: -0.1700
Data Index: 2662879 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8671. Min Act: -0.1700
Data Index: 2595834 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8359. Min Act: -0.1700
Data Index: 5744734 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8046. Min Act: -0.1700
Data Index: 3742365 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8046. Min Act: -0.1700
Data Index: 613067 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8046. Min Act: -0.1700
Data Index: 4088048 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.8046. Min Act: -0.1700
Data Index: 5500794 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.7734. Min Act: -0.1700
Data Index: 559993 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.7734. Min Act: -0.1700
Data Index: 4217299 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4921. Min Range: -5.4921
Max Act: 4.7734. Min Act: -0.1700
Data Index: 5221288 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19