Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3327. Min Range: -4.3327
Max Act: 4.3327. Min Act: -0.1700
Data Index: 1829452 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3327. Min Range: -4.3327
Max Act: 4.1765. Min Act: -0.1700
Data Index: 2946993 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3327. Min Range: -4.3327
Max Act: 4.1452. Min Act: -0.1700
Data Index: 339955 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3327. Min Range: -4.3327
Max Act: 4.0515. Min Act: -0.1700
Data Index: 1425948 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.9264. Min Act: -0.1700
Data Index: 789351 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.9264. Min Act: -0.1700
Data Index: 4393979 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8951. Min Act: -0.1700
Data Index: 5581096 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8951. Min Act: -0.1700
Data Index: 3303033 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5480726 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8326. Min Act: -0.1700
Data Index: 5227619 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8326. Min Act: -0.1700
Data Index: 4165226 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8326. Min Act: -0.1700
Data Index: 2376599 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8170. Min Act: -0.1700
Data Index: 7803642 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8013. Min Act: -0.1700
Data Index: 1666261 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.8013. Min Act: -0.1700
Data Index: 1994264 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.7857. Min Act: -0.1700
Data Index: 5345232 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.7701. Min Act: -0.1700
Data Index: 6128591 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.7857. Min Act: -0.1700
Data Index: 8051467 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.7701. Min Act: -0.1700
Data Index: 4375036 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3327. Min Range: -4.3327
Max Act: 3.7701. Min Act: -0.1700
Data Index: 2075118 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19