Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5331 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0269. Min Range: -5.0269
Max Act: 5.0269. Min Act: -0.1700
Data Index: 5084672 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.9644. Min Act: -0.1700
Data Index: 1309105 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.9019. Min Act: -0.1700
Data Index: 6428500 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4555145 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.9019. Min Act: -0.1700
Data Index: 1021229 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8706. Min Act: -0.1700
Data Index: 7111691 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8394. Min Act: -0.1700
Data Index: 1478013 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8394. Min Act: -0.1700
Data Index: 3060079 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8394. Min Act: -0.1700
Data Index: 2154281 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6397810 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 2775872 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 7478332 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 5525976 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 6870231 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.8081. Min Act: -0.1700
Data Index: 7458372 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.7769. Min Act: -0.1700
Data Index: 3890945 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.7769. Min Act: -0.1700
Data Index: 2520520 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3886518 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.7769. Min Act: -0.1700
Data Index: 228274 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0269. Min Range: -5.0269
Max Act: 4.7769. Min Act: -0.1700
Data Index: 6911321 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19