Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5468. Min Range: -7.5468
Max Act: 7.5468. Min Act: -0.1700
Data Index: 3225988 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5468. Min Range: -7.5468
Max Act: 7.1093. Min Act: -0.1700
Data Index: 4512990 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.9218. Min Act: -0.1700
Data Index: 1272348 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.8906. Min Act: -0.1700
Data Index: 490138 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.8906. Min Act: -0.1700
Data Index: 4524656 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.7968. Min Act: -0.1700
Data Index: 5423048 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.7656. Min Act: -0.1700
Data Index: 4769600 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.7343. Min Act: -0.1700
Data Index: 2858467 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.7656. Min Act: -0.1700
Data Index: 6664897 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.6718. Min Act: -0.1700
Data Index: 3814337 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.6093. Min Act: -0.1700
Data Index: 1945114 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.6093. Min Act: -0.1700
Data Index: 7607415 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2709624 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5781. Min Act: -0.1700
Data Index: 113359 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.6093. Min Act: -0.1700
Data Index: 4809176 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 5578494 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 3254299 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 7198708 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 2448077 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5468. Min Range: -7.5468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 7718450 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19