Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5080 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1454. Min Range: -5.1454
Max Act: 5.1454. Min Act: -0.1700
Data Index: 2856971 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1454. Min Range: -5.1454
Max Act: 5.0829. Min Act: -0.1700
Data Index: 3223047 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1454. Min Range: -5.1454
Max Act: 5.0204. Min Act: -0.1700
Data Index: 5664185 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9891. Min Act: -0.1700
Data Index: 3625894 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9579. Min Act: -0.1700
Data Index: 755050 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9266. Min Act: -0.1700
Data Index: 7440602 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9266. Min Act: -0.1700
Data Index: 7522756 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9266. Min Act: -0.1700
Data Index: 5937383 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1080575 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9266. Min Act: -0.1700
Data Index: 5806402 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.9266. Min Act: -0.1700
Data Index: 3061571 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8954. Min Act: -0.1700
Data Index: 1514202 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8641. Min Act: -0.1700
Data Index: 5347921 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8641. Min Act: -0.1700
Data Index: 4563616 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1629745 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8329. Min Act: -0.1700
Data Index: 5682279 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8016. Min Act: -0.1700
Data Index: 3606260 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8016. Min Act: -0.1700
Data Index: 3112455 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8016. Min Act: -0.1700
Data Index: 752257 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1454. Min Range: -5.1454
Max Act: 4.8016. Min Act: -0.1700
Data Index: 8197908 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19