Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4694 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5895. Min Act: -0.1700
Data Index: 1942048 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5720. Min Act: -0.1698
Data Index: 2566971 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5545. Min Act: -0.1700
Data Index: 3509408 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5194. Min Act: -0.1699
Data Index: 8720738 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5370. Min Act: -0.1700
Data Index: 3763907 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5194. Min Act: -0.1700
Data Index: 7222512 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5019. Min Act: -0.1700
Data Index: 106056 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5019. Min Act: -0.1700
Data Index: 2043820 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.5019. Min Act: -0.1699
Data Index: 8567299 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4843. Min Act: -0.1700
Data Index: 5956050 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4668. Min Act: -0.1699
Data Index: 5571649 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4843. Min Act: -0.1700
Data Index: 6396275 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4843. Min Act: -0.1699
Data Index: 3888138 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4492. Min Act: -0.1700
Data Index: 3883140 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4668. Min Act: -0.1700
Data Index: 3101860 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4492. Min Act: -0.1700
Data Index: 7487633 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4668. Min Act: -0.1697
Data Index: 7350653 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4668. Min Act: -0.1700
Data Index: 6864968 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4668. Min Act: -0.1700
Data Index: 1794670 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5895. Min Range: -1.5895
Max Act: 1.4492. Min Act: -0.1700
Data Index: 2515267 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19