Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.6828. Min Act: -0.1700
Data Index: 1415588 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.6828. Min Act: -0.1700
Data Index: 3317048 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.6203. Min Act: -0.1700
Data Index: 6475657 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.5578. Min Act: -0.1700
Data Index: 1095821 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 7168341 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 2383984 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 6272434 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 6174687 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 5816337 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 4452606 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 3876182 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 1695091 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 3420978 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 3078590 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 3030736 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 1184843 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 1153420 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 574845 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 2499109 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6828. Min Range: -7.6828
Max Act: 7.4953. Min Act: -0.1700
Data Index: 505384 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19