Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 6931499 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0040. Min Act: -0.1700
Data Index: 4693930 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9415. Min Act: -0.1700
Data Index: 6633214 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9415. Min Act: -0.1700
Data Index: 5470572 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 5260374 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9415. Min Act: -0.1700
Data Index: 7851854 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 2427213 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 2437177 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 55495 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9103. Min Act: -0.1700
Data Index: 5996807 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 8182508 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3067397 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 6071541 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8790. Min Act: -0.1700
Data Index: 229094 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 5710292 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 7827084 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1508458 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 2524270 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 6491896 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8165. Min Act: -0.1700
Data Index: 3058254 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19