Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 99 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.9891. Min Act: -0.1700
Data Index: 7644026 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8699266 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 603516 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 879449 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.7078. Min Act: -0.1700
Data Index: 8181330 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.6453. Min Act: -0.1700
Data Index: 8201225 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.6453. Min Act: -0.1700
Data Index: 5020233 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.6141. Min Act: -0.1700
Data Index: 782031 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5828. Min Act: -0.1700
Data Index: 1632599 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.6141. Min Act: -0.1700
Data Index: 6664958 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5516. Min Act: -0.1700
Data Index: 1117586 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5516. Min Act: -0.1700
Data Index: 2999914 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.4891. Min Act: -0.1700
Data Index: 3947091 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5203. Min Act: -0.1700
Data Index: 7627358 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5516. Min Act: -0.1700
Data Index: 2066345 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5203. Min Act: -0.1700
Data Index: 877252 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.4891. Min Act: -0.1700
Data Index: 4616405 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.5203. Min Act: -0.1700
Data Index: 6337910 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.4578. Min Act: -0.1700
Data Index: 1158563 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9891. Min Range: -5.9891
Max Act: 5.4578. Min Act: -0.1700
Data Index: 7557731 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19