Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1493. Min Range: -8.1493
Max Act: 8.1493. Min Act: -0.1700
Data Index: 5744997 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1493. Min Range: -8.1493
Max Act: 8.1493. Min Act: -0.1700
Data Index: 3135606 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1493. Min Range: -8.1493
Max Act: 8.0868. Min Act: -0.1700
Data Index: 2306630 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1493. Min Range: -8.1493
Max Act: 8.0555. Min Act: -0.1700
Data Index: 650794 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1493. Min Range: -8.1493
Max Act: 8.0243. Min Act: -0.1700
Data Index: 2746113 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9930. Min Act: -0.1700
Data Index: 5316165 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9305. Min Act: -0.1700
Data Index: 6672832 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9930. Min Act: -0.1700
Data Index: 4940335 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9930. Min Act: -0.1700
Data Index: 3345030 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9618. Min Act: -0.1700
Data Index: 6829505 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8993. Min Act: -0.1700
Data Index: 8387749 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8993. Min Act: -0.1700
Data Index: 4054922 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.9305. Min Act: -0.1700
Data Index: 977088 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8680. Min Act: -0.1700
Data Index: 3927298 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8680. Min Act: -0.1700
Data Index: 7819152 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8368. Min Act: -0.1700
Data Index: 135784 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8368. Min Act: -0.1700
Data Index: 3658891 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8680. Min Act: -0.1700
Data Index: 7559402 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.8368. Min Act: -0.1700
Data Index: 377220 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1493. Min Range: -8.1493
Max Act: 7.7743. Min Act: -0.1700
Data Index: 6997797 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19