Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.9722. Min Act: -0.1700
Data Index: 5253953 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.8136. Min Act: -0.1700
Data Index: 3378280 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7019. Min Act: -0.1700
Data Index: 6819286 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6538. Min Act: -0.1700
Data Index: 4705591 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6859. Min Act: -0.1700
Data Index: 684074 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6378. Min Act: -0.1700
Data Index: 3222362 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6378. Min Act: -0.1700
Data Index: 7068 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6378. Min Act: -0.1700
Data Index: 7286814 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6217. Min Act: -0.1700
Data Index: 1815899 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6378. Min Act: -0.1700
Data Index: 946260 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6056. Min Act: -0.1700
Data Index: 6295334 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6056. Min Act: -0.1700
Data Index: 7429052 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6056. Min Act: -0.1700
Data Index: 6206837 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5895. Min Act: -0.1700
Data Index: 7116270 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5895. Min Act: -0.1700
Data Index: 2266361 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.6056. Min Act: -0.1700
Data Index: 5764448 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5734. Min Act: -0.1700
Data Index: 4302189 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5412. Min Act: -0.1700
Data Index: 6712142 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5573. Min Act: -0.1700
Data Index: 7168485 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.5250. Min Act: -0.1700
Data Index: 7116280 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19