Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1453. Min Range: -6.1453
Max Act: 6.1453. Min Act: -0.1700
Data Index: 277749 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1453. Min Range: -6.1453
Max Act: 6.1141. Min Act: -0.1700
Data Index: 2898912 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1453. Min Range: -6.1453
Max Act: 6.1141. Min Act: -0.1700
Data Index: 7429645 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1453. Min Range: -6.1453
Max Act: 6.0828. Min Act: -0.1700
Data Index: 6783498 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4798409 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4786318 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 2431524 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2363461 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 913705 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3284246 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7726941 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 5193429 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 8185236 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 8827094 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.9266. Min Act: -0.1700
Data Index: 6182776 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8953. Min Act: -0.1700
Data Index: 758806 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8641. Min Act: -0.1700
Data Index: 7642631 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8641. Min Act: -0.1700
Data Index: 3982396 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8641. Min Act: -0.1700
Data Index: 1156875 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1453. Min Range: -6.1453
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5462484 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19