Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.3152. Min Act: -0.1700
Data Index: 4506858 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.2215. Min Act: -0.1700
Data Index: 2357585 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.1902. Min Act: -0.1700
Data Index: 6112318 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.0340. Min Act: -0.1700
Data Index: 6282927 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.0340. Min Act: -0.1700
Data Index: 3793252 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.0027. Min Act: -0.1700
Data Index: 8629590 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.0027. Min Act: -0.1700
Data Index: 612276 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3152. Min Range: -7.3152
Max Act: 7.0027. Min Act: -0.1700
Data Index: 3086371 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9715. Min Act: -0.1700
Data Index: 3164264 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9715. Min Act: -0.1700
Data Index: 3127438 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9402. Min Act: -0.1700
Data Index: 1986705 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9402. Min Act: -0.1700
Data Index: 2253062 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9090. Min Act: -0.1700
Data Index: 5043440 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8777. Min Act: -0.1700
Data Index: 1342304 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.9090. Min Act: -0.1700
Data Index: 6654850 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8777. Min Act: -0.1700
Data Index: 2628429 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8465. Min Act: -0.1700
Data Index: 4952738 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8465. Min Act: -0.1700
Data Index: 3492630 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8465. Min Act: -0.1700
Data Index: 5363979 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3152. Min Range: -7.3152
Max Act: 6.8465. Min Act: -0.1700
Data Index: 6111777 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19