Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1990. Min Range: -6.1990
Max Act: 6.1990. Min Act: -0.1700
Data Index: 3885045 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1990. Min Range: -6.1990
Max Act: 6.1678. Min Act: -0.1700
Data Index: 4075865 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1990. Min Range: -6.1990
Max Act: 6.0115. Min Act: -0.1700
Data Index: 17555 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1990. Min Range: -6.1990
Max Act: 6.0115. Min Act: -0.1700
Data Index: 5047195 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9803. Min Act: -0.1700
Data Index: 6749462 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9803. Min Act: -0.1700
Data Index: 8689630 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9490. Min Act: -0.1700
Data Index: 4910414 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9490. Min Act: -0.1700
Data Index: 2176849 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9490. Min Act: -0.1700
Data Index: 4980836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9178. Min Act: -0.1700
Data Index: 6376142 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9178. Min Act: -0.1700
Data Index: 2163598 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9178. Min Act: -0.1700
Data Index: 8161850 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.9178. Min Act: -0.1700
Data Index: 3110487 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.8553. Min Act: -0.1700
Data Index: 6977511 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.8553. Min Act: -0.1700
Data Index: 1474076 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.8553. Min Act: -0.1700
Data Index: 6078446 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.8553. Min Act: -0.1700
Data Index: 5487820 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.7928. Min Act: -0.1700
Data Index: 6800466 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.7928. Min Act: -0.1700
Data Index: 4441885 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1990. Min Range: -6.1990
Max Act: 5.7615. Min Act: -0.1700
Data Index: 4618443 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19