Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4534 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1114. Min Range: -8.1114
Max Act: 8.1114. Min Act: -0.1700
Data Index: 4121045 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.9864. Min Act: -0.1700
Data Index: 3773479 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.8614. Min Act: -0.1700
Data Index: 7746789 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.8614. Min Act: -0.1700
Data Index: 1652040 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7989. Min Act: -0.1700
Data Index: 342118 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7676. Min Act: -0.1700
Data Index: 3755637 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.8301. Min Act: -0.1700
Data Index: 2842024 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7676. Min Act: -0.1700
Data Index: 7007071 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7676. Min Act: -0.1700
Data Index: 1572505 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7676. Min Act: -0.1700
Data Index: 3715720 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7051. Min Act: -0.1700
Data Index: 3068694 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7051. Min Act: -0.1700
Data Index: 1270999 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.7051. Min Act: -0.1700
Data Index: 2911896 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6739. Min Act: -0.1700
Data Index: 5510828 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6739. Min Act: -0.1700
Data Index: 2346445 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6426. Min Act: -0.1700
Data Index: 7249381 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6426. Min Act: -0.1700
Data Index: 6102571 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6114. Min Act: -0.1700
Data Index: 5141161 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6114. Min Act: -0.1700
Data Index: 2911892 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1114. Min Range: -8.1114
Max Act: 7.6114. Min Act: -0.1700
Data Index: 6531896 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19