Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4348 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.5265. Min Act: -0.1700
Data Index: 4348634 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.4640. Min Act: -0.1700
Data Index: 6343303 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.4640. Min Act: -0.1700
Data Index: 8301943 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.4015. Min Act: -0.1700
Data Index: 5138470 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.4015. Min Act: -0.1700
Data Index: 4382656 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.1515. Min Act: -0.1700
Data Index: 591673 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.1515. Min Act: -0.1700
Data Index: 2257782 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 7815992 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 6997747 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 848098 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 7955493 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0890. Min Act: -0.1700
Data Index: 2266709 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 8550155 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5265. Min Range: -9.5265
Max Act: 9.0265. Min Act: -0.1700
Data Index: 4439197 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 630456 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 4021741 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 638706 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 6727831 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 5121812 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5265. Min Range: -9.5265
Max Act: 8.9640. Min Act: -0.1700
Data Index: 7824968 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19