Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1584. Min Range: -6.1584
Max Act: 6.1584. Min Act: -0.1700
Data Index: 4747350 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.9709. Min Act: -0.1700
Data Index: 3771823 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.9396. Min Act: -0.1700
Data Index: 3771824 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.9084. Min Act: -0.1700
Data Index: 3725181 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.7209. Min Act: -0.1700
Data Index: 7377146 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.7209. Min Act: -0.1700
Data Index: 830750 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6584. Min Act: -0.1700
Data Index: 1968429 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6896. Min Act: -0.1700
Data Index: 1117949 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6271. Min Act: -0.1700
Data Index: 6428927 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6271. Min Act: -0.1700
Data Index: 1573923 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6271. Min Act: -0.1700
Data Index: 449448 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6271. Min Act: -0.1700
Data Index: 1737637 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.6271. Min Act: -0.1700
Data Index: 6315807 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5959. Min Act: -0.1700
Data Index: 624424 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5959. Min Act: -0.1700
Data Index: 7853540 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5646. Min Act: -0.1700
Data Index: 980223 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5646. Min Act: -0.1700
Data Index: 4147207 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5646. Min Act: -0.1700
Data Index: 474735 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5021. Min Act: -0.1700
Data Index: 8374706 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1584. Min Range: -6.1584
Max Act: 5.5334. Min Act: -0.1700
Data Index: 889678 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19