Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.8014. Min Act: -0.1700
Data Index: 8058408 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6764. Min Act: -0.1700
Data Index: 6316549 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.7076. Min Act: -0.1700
Data Index: 1140866 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6451. Min Act: -0.1700
Data Index: 569119 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6139. Min Act: -0.1700
Data Index: 5199253 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6139. Min Act: -0.1700
Data Index: 5993918 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6139. Min Act: -0.1700
Data Index: 7723773 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.6139. Min Act: -0.1700
Data Index: 148351 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.5201. Min Act: -0.1700
Data Index: 6408596 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.5201. Min Act: -0.1700
Data Index: 8164120 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.5201. Min Act: -0.1700
Data Index: 3173467 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4889. Min Act: -0.1700
Data Index: 183795 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4889. Min Act: -0.1700
Data Index: 4918056 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4889. Min Act: -0.1700
Data Index: 6923939 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4576. Min Act: -0.1700
Data Index: 781958 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4264. Min Act: -0.1700
Data Index: 4536889 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4576. Min Act: -0.1700
Data Index: 5049093 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.3951. Min Act: -0.1700
Data Index: 3281753 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4264. Min Act: -0.1700
Data Index: 6708297 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8014. Min Range: -7.8014
Max Act: 7.4264. Min Act: -0.1700
Data Index: 3266531 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19