Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.8850. Min Act: -0.1700
Data Index: 3566727 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.6975. Min Act: -0.1700
Data Index: 8758285 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.6662. Min Act: -0.1700
Data Index: 8325629 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.4787. Min Act: -0.1700
Data Index: 19894 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.5412. Min Act: -0.1700
Data Index: 689698 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.5100. Min Act: -0.1700
Data Index: 2987826 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.4475. Min Act: -0.1700
Data Index: 7273640 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.4475. Min Act: -0.1700
Data Index: 5169223 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.4475. Min Act: -0.1700
Data Index: 3554081 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.3225. Min Act: -0.1700
Data Index: 1512234 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5132307 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.3225. Min Act: -0.1700
Data Index: 7767560 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5770246 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2600. Min Act: -0.1700
Data Index: 1682626 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2600. Min Act: -0.1700
Data Index: 7689924 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2912. Min Act: -0.1700
Data Index: 2888140 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2600. Min Act: -0.1700
Data Index: 3113473 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2287. Min Act: -0.1700
Data Index: 2968101 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2287. Min Act: -0.1700
Data Index: 1086926 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8850. Min Range: -6.8850
Max Act: 6.2287. Min Act: -0.1700
Data Index: 7520937 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19