Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0266. Min Range: -6.0266
Max Act: 6.0266. Min Act: -0.1700
Data Index: 1069413 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.7766. Min Act: -0.1700
Data Index: 1046872 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2089544 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.7453. Min Act: -0.1700
Data Index: 2782086 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.7141. Min Act: -0.1700
Data Index: 2241741 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 2742167 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6516. Min Act: -0.1700
Data Index: 1564184 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5061688 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6516. Min Act: -0.1700
Data Index: 2347059 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5256325 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 6272798 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 4299806 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 3338943 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5891. Min Act: -0.1700
Data Index: 4237480 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5891. Min Act: -0.1700
Data Index: 6251752 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5578. Min Act: -0.1700
Data Index: 1057918 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.6203. Min Act: -0.1700
Data Index: 5823053 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5891. Min Act: -0.1700
Data Index: 3001098 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5891. Min Act: -0.1700
Data Index: 5499506 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0266. Min Range: -6.0266
Max Act: 5.5891. Min Act: -0.1700
Data Index: 5999815 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19