Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.4076. Min Act: -0.1700
Data Index: 4246877 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.2826. Min Act: -0.1700
Data Index: 1276936 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.2201. Min Act: -0.1700
Data Index: 5463386 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 5690237 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.1888. Min Act: -0.1700
Data Index: 4912348 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.1576. Min Act: -0.1700
Data Index: 7656598 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0638. Min Act: -0.1700
Data Index: 392541 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0638. Min Act: -0.1700
Data Index: 361779 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0638. Min Act: -0.1700
Data Index: 6808438 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.9388. Min Act: -0.1700
Data Index: 2748618 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0638. Min Act: -0.1700
Data Index: 7305927 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0326. Min Act: -0.1699
Data Index: 151988 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4076. Min Range: -5.4076
Max Act: 5.0326. Min Act: -0.1700
Data Index: 4305866 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.9701. Min Act: -0.1700
Data Index: 2916244 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.9701. Min Act: -0.1700
Data Index: 6848306 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.7513. Min Act: -0.1700
Data Index: 542171 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.7826. Min Act: -0.1700
Data Index: 4986680 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.7513. Min Act: -0.1700
Data Index: 5507067 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.7826. Min Act: -0.1700
Data Index: 3157079 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4076. Min Range: -5.4076
Max Act: 4.8138. Min Act: -0.1699
Data Index: 6164135 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19