Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.9231. Min Act: -0.1700
Data Index: 5236285 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.9231. Min Act: -0.1700
Data Index: 2489798 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.8293. Min Act: -0.1700
Data Index: 4852215 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.7981. Min Act: -0.1700
Data Index: 6243836 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.8293. Min Act: -0.1700
Data Index: 5279086 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.7668. Min Act: -0.1700
Data Index: 3387415 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.7356. Min Act: -0.1700
Data Index: 1001663 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 5487246 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 6776651 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 2118666 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 5555134 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 356782 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6418. Min Act: -0.1700
Data Index: 938530 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6418. Min Act: -0.1700
Data Index: 3478096 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6731. Min Act: -0.1700
Data Index: 5595755 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6418. Min Act: -0.1700
Data Index: 1217037 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6106. Min Act: -0.1700
Data Index: 2785414 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6106. Min Act: -0.1700
Data Index: 1913984 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6418. Min Act: -0.1700
Data Index: 3261327 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9231. Min Range: -5.9231
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6402541 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19