Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0013. Min Range: -5.0013
Max Act: 5.0013. Min Act: -0.1700
Data Index: 3109097 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.9076. Min Act: -0.1700
Data Index: 6540676 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7826. Min Act: -0.1700
Data Index: 8185860 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7513. Min Act: -0.1700
Data Index: 2372353 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7513. Min Act: -0.1700
Data Index: 7782271 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7201. Min Act: -0.1700
Data Index: 2798079 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7201. Min Act: -0.1700
Data Index: 5502853 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7201. Min Act: -0.1700
Data Index: 427147 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6888. Min Act: -0.1700
Data Index: 8152389 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6888. Min Act: -0.1700
Data Index: 3436273 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.7201. Min Act: -0.1700
Data Index: 2882565 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6576. Min Act: -0.1700
Data Index: 4526525 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6576. Min Act: -0.1700
Data Index: 2906673 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6263. Min Act: -0.1700
Data Index: 1672292 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.6576. Min Act: -0.1700
Data Index: 642056 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.5951. Min Act: -0.1700
Data Index: 5295234 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.5951. Min Act: -0.1700
Data Index: 2931944 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.5638. Min Act: -0.1700
Data Index: 1483865 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.5638. Min Act: -0.1700
Data Index: 3338512 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0013. Min Range: -5.0013
Max Act: 4.5638. Min Act: -0.1700
Data Index: 771662 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19