Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 383 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.8274. Min Act: -0.1700
Data Index: 1417116 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5297710 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.7024. Min Act: -0.1700
Data Index: 1425234 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6711. Min Act: -0.1700
Data Index: 5507347 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6399. Min Act: -0.1700
Data Index: 6042877 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6399. Min Act: -0.1700
Data Index: 285268 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6399. Min Act: -0.1700
Data Index: 8317415 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4721854 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6086. Min Act: -0.1700
Data Index: 832850 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6086. Min Act: -0.1700
Data Index: 4927761 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6086. Min Act: -0.1700
Data Index: 4397771 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6086. Min Act: -0.1700
Data Index: 487534 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.6086. Min Act: -0.1700
Data Index: 60124 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 5502674 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 8064433 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4030976 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 1631388 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 22792 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 5200317 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8274. Min Range: -5.8274
Max Act: 5.5774. Min Act: -0.1700
Data Index: 3571601 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19