Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1216 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0646. Min Range: -8.0646
Max Act: 8.0646. Min Act: -0.1700
Data Index: 7714915 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0646. Min Range: -8.0646
Max Act: 8.0646. Min Act: -0.1700
Data Index: 2358797 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.9396. Min Act: -0.1700
Data Index: 8642231 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.9396. Min Act: -0.1700
Data Index: 5475751 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.8459. Min Act: -0.1700
Data Index: 1526773 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7834. Min Act: -0.1700
Data Index: 6375302 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7834. Min Act: -0.1700
Data Index: 7583186 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.8146. Min Act: -0.1700
Data Index: 4666563 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7834. Min Act: -0.1700
Data Index: 8154157 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7521. Min Act: -0.1700
Data Index: 2704995 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7521. Min Act: -0.1700
Data Index: 7196150 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.7521. Min Act: -0.1700
Data Index: 815519 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6584. Min Act: -0.1700
Data Index: 3491222 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6584. Min Act: -0.1700
Data Index: 955031 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6271. Min Act: -0.1700
Data Index: 5258467 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6271. Min Act: -0.1700
Data Index: 7163414 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6271. Min Act: -0.1700
Data Index: 3753935 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.6271. Min Act: -0.1700
Data Index: 5106728 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.5646. Min Act: -0.1700
Data Index: 5775055 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0646. Min Range: -8.0646
Max Act: 7.5959. Min Act: -0.1700
Data Index: 1248240 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19