Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1460 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.6455. Min Act: -0.1700
Data Index: 5390431 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.6142. Min Act: -0.1700
Data Index: 3386854 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5516. Min Act: -0.1700
Data Index: 4983510 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5359. Min Act: -0.1700
Data Index: 875580 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5359. Min Act: -0.1700
Data Index: 1533808 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5203. Min Act: -0.1700
Data Index: 835500 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5046. Min Act: -0.1700
Data Index: 4549729 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5046. Min Act: -0.1700
Data Index: 4939768 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4889. Min Act: -0.1700
Data Index: 6604545 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.5046. Min Act: -0.1700
Data Index: 6485177 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4733. Min Act: -0.1700
Data Index: 6103595 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4576. Min Act: -0.1700
Data Index: 8095289 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4733. Min Act: -0.1700
Data Index: 4713464 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4419. Min Act: -0.1700
Data Index: 5319862 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4419. Min Act: -0.1700
Data Index: 7227388 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4263. Min Act: -0.1700
Data Index: 623555 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4576. Min Act: -0.1700
Data Index: 659758 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4263. Min Act: -0.1700
Data Index: 4380357 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4263. Min Act: -0.1700
Data Index: 4717891 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6455. Min Range: -3.6455
Max Act: 3.4263. Min Act: -0.1700
Data Index: 2667313 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19