Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.3274. Min Act: -0.1700
Data Index: 3868948 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.2961. Min Act: -0.1700
Data Index: 7489608 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.2336. Min Act: -0.1700
Data Index: 569978 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.2336. Min Act: -0.1700
Data Index: 1418866 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.2024. Min Act: -0.1700
Data Index: 8301860 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.0461. Min Act: -0.1700
Data Index: 7314430 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.0774. Min Act: -0.1700
Data Index: 5859124 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.0149. Min Act: -0.1700
Data Index: 2741882 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3274. Min Range: -6.3274
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3195595 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.9836. Min Act: -0.1700
Data Index: 1133871 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.9524. Min Act: -0.1700
Data Index: 5507462 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.9524. Min Act: -0.1700
Data Index: 2469413 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8899. Min Act: -0.1700
Data Index: 1237121 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8899. Min Act: -0.1700
Data Index: 4791135 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8586. Min Act: -0.1700
Data Index: 3805848 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8586. Min Act: -0.1700
Data Index: 5418203 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8274. Min Act: -0.1700
Data Index: 1461360 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8274. Min Act: -0.1700
Data Index: 6744142 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8274. Min Act: -0.1700
Data Index: 7237850 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3274. Min Range: -6.3274
Max Act: 5.8274. Min Act: -0.1700
Data Index: 2620650 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19