Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1894. Min Range: -5.1894
Max Act: 5.1894. Min Act: -0.1700
Data Index: 36435 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1894. Min Range: -5.1894
Max Act: 5.0957. Min Act: -0.1700
Data Index: 7462668 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1894. Min Range: -5.1894
Max Act: 5.0957. Min Act: -0.1700
Data Index: 7312658 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1894. Min Range: -5.1894
Max Act: 5.0644. Min Act: -0.1700
Data Index: 7034548 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1894. Min Range: -5.1894
Max Act: 5.0332. Min Act: -0.1700
Data Index: 66538 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9707. Min Act: -0.1700
Data Index: 5287310 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9394. Min Act: -0.1700
Data Index: 1359490 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9394. Min Act: -0.1700
Data Index: 379633 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9082. Min Act: -0.1700
Data Index: 6621025 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9082. Min Act: -0.1700
Data Index: 3475495 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9082. Min Act: -0.1700
Data Index: 2830045 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9082. Min Act: -0.1700
Data Index: 3214234 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8769. Min Act: -0.1700
Data Index: 8203201 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8769. Min Act: -0.1700
Data Index: 3140737 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8457. Min Act: -0.1700
Data Index: 7499957 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8769. Min Act: -0.1700
Data Index: 2290684 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.9082. Min Act: -0.1700
Data Index: 5986206 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8457. Min Act: -0.1700
Data Index: 4453258 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8457. Min Act: -0.1700
Data Index: 7923940 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1894. Min Range: -5.1894
Max Act: 4.8144. Min Act: -0.1700
Data Index: 149333 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19