Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.7391. Min Act: -0.1700
Data Index: 5084049 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.6766. Min Act: -0.1700
Data Index: 4878724 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.6453. Min Act: -0.1700
Data Index: 114725 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.6141. Min Act: -0.1700
Data Index: 5782656 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.6453. Min Act: -0.1700
Data Index: 6208532 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.6141. Min Act: -0.1700
Data Index: 7532798 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5828. Min Act: -0.1700
Data Index: 8019908 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5828. Min Act: -0.1700
Data Index: 2884186 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5828. Min Act: -0.1700
Data Index: 7367440 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 5089716 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 2217336 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 8778538 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 5619340 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 3395090 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5203. Min Act: -0.1700
Data Index: 4382110 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5203. Min Act: -0.1700
Data Index: 7717551 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5516. Min Act: -0.1700
Data Index: 5568574 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.4890. Min Act: -0.1700
Data Index: 3299344 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.5203. Min Act: -0.1700
Data Index: 5060433 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7391. Min Range: -4.7391
Max Act: 4.4578. Min Act: -0.1699
Data Index: 5018751 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19