Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3891. Min Act: -0.1700
Data Index: 7289218 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3578. Min Act: -0.1700
Data Index: 7050335 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3578. Min Act: -0.1700
Data Index: 7289219 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3266. Min Act: -0.1700
Data Index: 1162464 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.3266. Min Act: -0.1700
Data Index: 6640352 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2953. Min Act: -0.1700
Data Index: 4367738 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2328. Min Act: -0.1700
Data Index: 7272235 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2016. Min Act: -0.1700
Data Index: 5342553 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2328. Min Act: -0.1700
Data Index: 8158172 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2016. Min Act: -0.1700
Data Index: 7654195 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.2016. Min Act: -0.1700
Data Index: 6431974 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 8310880 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 2412399 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7119843 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 5800256 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 84585 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 5725054 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 5567642 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7254887 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3891. Min Range: -6.3891
Max Act: 6.1703. Min Act: -0.1700
Data Index: 7147044 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19