Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5413 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.6579. Min Act: -0.1700
Data Index: 4447548 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.1579. Min Act: -0.1700
Data Index: 3701608 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.1579. Min Act: -0.1700
Data Index: 4369513 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.1579. Min Act: -0.1700
Data Index: 3409467 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.0329. Min Act: -0.1700
Data Index: 5680154 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.0954. Min Act: -0.1700
Data Index: 1892369 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9704. Min Act: -0.1700
Data Index: 8633123 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6579. Min Range: -9.6579
Max Act: 9.0954. Min Act: -0.1700
Data Index: 2586497 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9704. Min Act: -0.1700
Data Index: 8571045 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 3837472 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 5186509 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 436046 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 6631096 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 8036253 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 2181656 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.8454. Min Act: -0.1700
Data Index: 1858798 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 99355 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.8454. Min Act: -0.1700
Data Index: 1164627 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.7829. Min Act: -0.1700
Data Index: 2589444 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6579. Min Range: -9.6579
Max Act: 8.9079. Min Act: -0.1700
Data Index: 5389095 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19