Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1634. Min Act: -0.1700
Data Index: 356920 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1634. Min Act: -0.1700
Data Index: 4825311 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1322. Min Act: -0.1700
Data Index: 356926 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1009. Min Act: -0.1700
Data Index: 1570059 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9447. Min Act: -0.1700
Data Index: 2451010 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8822. Min Act: -0.1700
Data Index: 4533277 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8509. Min Act: -0.1700
Data Index: 7605840 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8822. Min Act: -0.1700
Data Index: 7421396 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8822. Min Act: -0.1700
Data Index: 7825235 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8509. Min Act: -0.1700
Data Index: 7388705 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8822. Min Act: -0.1700
Data Index: 4356561 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8509. Min Act: -0.1700
Data Index: 7221257 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8509. Min Act: -0.1700
Data Index: 4425553 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8197. Min Act: -0.1700
Data Index: 6733047 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.8197. Min Act: -0.1700
Data Index: 6809707 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.7884. Min Act: -0.1700
Data Index: 7609533 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.7884. Min Act: -0.1700
Data Index: 675925 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.7884. Min Act: -0.1700
Data Index: 4535940 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.7572. Min Act: -0.1700
Data Index: 4500148 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1762771 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19