Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4065851 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2163337 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8893. Min Act: -0.1700
Data Index: 6060476 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8581. Min Act: -0.1700
Data Index: 2053888 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8737. Min Act: -0.1700
Data Index: 8108965 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8737. Min Act: -0.1700
Data Index: 5656125 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8424. Min Act: -0.1700
Data Index: 5008229 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8268. Min Act: -0.1700
Data Index: 7624574 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8424. Min Act: -0.1700
Data Index: 5595553 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7955. Min Act: -0.1700
Data Index: 6921211 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7799. Min Act: -0.1700
Data Index: 2788103 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8424. Min Act: -0.1700
Data Index: 3690229 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8112. Min Act: -0.1700
Data Index: 783338 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.8268. Min Act: -0.1700
Data Index: 576674 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7955. Min Act: -0.1700
Data Index: 5821054 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7955. Min Act: -0.1700
Data Index: 4800680 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7955. Min Act: -0.1700
Data Index: 614879 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7643. Min Act: -0.1700
Data Index: 8199775 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7643. Min Act: -0.1700
Data Index: 4626311 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9675. Min Range: -3.9675
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6451674 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19