Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5505 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.5599. Min Act: -0.1700
Data Index: 461514 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.5129. Min Act: -0.1700
Data Index: 8235055 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.4973. Min Act: -0.1700
Data Index: 2252644 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.3562. Min Act: -0.1700
Data Index: 6656168 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.3248. Min Act: -0.1700
Data Index: 2239907 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.3248. Min Act: -0.1700
Data Index: 1837621 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.3091. Min Act: -0.1700
Data Index: 2390014 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2934. Min Act: -0.1700
Data Index: 2934668 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2934. Min Act: -0.1700
Data Index: 157586 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2777. Min Act: -0.1700
Data Index: 7693554 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2463. Min Act: -0.1700
Data Index: 3151538 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2463. Min Act: -0.1700
Data Index: 6165684 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2149. Min Act: -0.1700
Data Index: 6877841 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2306. Min Act: -0.1700
Data Index: 2390032 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2306. Min Act: -0.1700
Data Index: 8088391 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2149. Min Act: -0.1700
Data Index: 4852527 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.2149. Min Act: -0.1700
Data Index: 8118132 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.1834. Min Act: -0.1700
Data Index: 1220913 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.1991. Min Act: -0.1700
Data Index: 2859247 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5599. Min Range: -3.5599
Max Act: 3.1991. Min Act: -0.1700
Data Index: 4416876 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19