Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.2308. Min Act: -0.1700
Data Index: 4524335 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8871. Min Act: -0.1700
Data Index: 4877052 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 368765 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 1687808 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7933. Min Act: -0.1700
Data Index: 7196420 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 5155394 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 3414057 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6996. Min Act: -0.1700
Data Index: 2656582 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 630745 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 324792 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 4672334 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6058. Min Act: -0.1700
Data Index: 8096949 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6371. Min Act: -0.1700
Data Index: 6108687 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6371. Min Act: -0.1700
Data Index: 6231014 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6058. Min Act: -0.1700
Data Index: 6147727 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.6058. Min Act: -0.1700
Data Index: 2760274 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.5746. Min Act: -0.1700
Data Index: 5942565 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.5746. Min Act: -0.1700
Data Index: 1167425 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.5433. Min Act: -0.1700
Data Index: 6270923 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.5433. Min Act: -0.1700
Data Index: 6103600 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19