Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1538. Min Range: -7.1538
Max Act: 7.1538. Min Act: -0.1700
Data Index: 1188784 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.8725. Min Act: -0.1700
Data Index: 7601556 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.8725. Min Act: -0.1700
Data Index: 3593881 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.8413. Min Act: -0.1700
Data Index: 80694 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.8100. Min Act: -0.1700
Data Index: 8605449 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.7788. Min Act: -0.1700
Data Index: 8423072 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.7163. Min Act: -0.1700
Data Index: 8551072 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6850. Min Act: -0.1700
Data Index: 7412301 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.7163. Min Act: -0.1700
Data Index: 3656740 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6850. Min Act: -0.1700
Data Index: 1326434 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6850. Min Act: -0.1700
Data Index: 8507389 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6850. Min Act: -0.1700
Data Index: 3123371 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6538. Min Act: -0.1700
Data Index: 1909372 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6538. Min Act: -0.1700
Data Index: 4306665 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6538. Min Act: -0.1700
Data Index: 7247584 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6225. Min Act: -0.1700
Data Index: 339393 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6225. Min Act: -0.1700
Data Index: 3451881 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6225. Min Act: -0.1700
Data Index: 4678886 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.6225. Min Act: -0.1700
Data Index: 6290877 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1538. Min Range: -7.1538
Max Act: 6.5913. Min Act: -0.1700
Data Index: 2418160 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19