Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0042. Min Range: -9.0042
Max Act: 9.0042. Min Act: -0.1700
Data Index: 3567623 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0042. Min Range: -9.0042
Max Act: 8.5042. Min Act: -0.1700
Data Index: 2044726 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0042. Min Range: -9.0042
Max Act: 8.4417. Min Act: -0.1700
Data Index: 7168492 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0042. Min Range: -9.0042
Max Act: 8.0667. Min Act: -0.1700
Data Index: 2306209 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0042. Min Range: -9.0042
Max Act: 8.0042. Min Act: -0.1700
Data Index: 7787142 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.9417. Min Act: -0.1700
Data Index: 4560461 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.9104. Min Act: -0.1700
Data Index: 6668447 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.8479. Min Act: -0.1700
Data Index: 7573694 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.8167. Min Act: -0.1700
Data Index: 1421303 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.7854. Min Act: -0.1700
Data Index: 4153548 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.7229. Min Act: -0.1700
Data Index: 5558245 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.7229. Min Act: -0.1700
Data Index: 7575086 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6917. Min Act: -0.1700
Data Index: 2360765 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6604. Min Act: -0.1700
Data Index: 6668448 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6604. Min Act: -0.1700
Data Index: 4987001 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6604. Min Act: -0.1700
Data Index: 6817759 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6604. Min Act: -0.1700
Data Index: 5915457 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6292. Min Act: -0.1700
Data Index: 4004537 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6604. Min Act: -0.1700
Data Index: 3133640 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0042. Min Range: -9.0042
Max Act: 7.6292. Min Act: -0.1700
Data Index: 676867 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19