Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.8264. Min Act: -0.1700
Data Index: 5776578 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.7327. Min Act: -0.1700
Data Index: 7262295 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.5764. Min Act: -0.1700
Data Index: 5231040 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.4514. Min Act: -0.1700
Data Index: 2001956 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.4514. Min Act: -0.1700
Data Index: 83564 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.3264. Min Act: -0.1700
Data Index: 1111882 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.3264. Min Act: -0.1700
Data Index: 4048985 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.2327. Min Act: -0.1700
Data Index: 3883974 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.2327. Min Act: -0.1700
Data Index: 5176365 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.2327. Min Act: -0.1700
Data Index: 6205113 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.2014. Min Act: -0.1700
Data Index: 3883966 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.2014. Min Act: -0.1700
Data Index: 2625106 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1702. Min Act: -0.1700
Data Index: 7854781 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1389. Min Act: -0.1700
Data Index: 2390606 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1389. Min Act: -0.1700
Data Index: 6932426 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1389. Min Act: -0.1700
Data Index: 6289116 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1389. Min Act: -0.1700
Data Index: 7238829 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.1077. Min Act: -0.1700
Data Index: 8302228 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.0764. Min Act: -0.1700
Data Index: 194752 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8264. Min Range: -7.8264
Max Act: 7.0764. Min Act: -0.1700
Data Index: 4778398 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19