Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 639 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.5348. Min Act: -0.1700
Data Index: 5012111 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.4723. Min Act: -0.1700
Data Index: 8068234 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.4098. Min Act: -0.1700
Data Index: 2028252 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.4098. Min Act: -0.1700
Data Index: 1171341 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.3785. Min Act: -0.1700
Data Index: 5288781 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.3160. Min Act: -0.1700
Data Index: 2847622 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.3160. Min Act: -0.1700
Data Index: 1171337 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2848. Min Act: -0.1700
Data Index: 760432 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2535. Min Act: -0.1700
Data Index: 4427871 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2848. Min Act: -0.1700
Data Index: 886320 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2535. Min Act: -0.1700
Data Index: 7817427 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2535. Min Act: -0.1700
Data Index: 8548874 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7029731 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7402334 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.2223. Min Act: -0.1700
Data Index: 4087193 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.1910. Min Act: -0.1700
Data Index: 230606 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.1910. Min Act: -0.1700
Data Index: 1302768 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7252098 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.1910. Min Act: -0.1700
Data Index: 4544749 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5348. Min Range: -5.5348
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7252099 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19