Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2463 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.1373. Min Act: -0.1700
Data Index: 1980380 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.1058. Min Act: -0.1700
Data Index: 8173336 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.1058. Min Act: -0.1700
Data Index: 1513762 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.1058. Min Act: -0.1700
Data Index: 6686547 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0900. Min Act: -0.1700
Data Index: 5109525 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0900. Min Act: -0.1700
Data Index: 6972346 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0900. Min Act: -0.1700
Data Index: 6609514 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 3454299 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0743. Min Act: -0.1700
Data Index: 1413835 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 2116174 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 7113981 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 3651471 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 634852 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0585. Min Act: -0.1700
Data Index: 298686 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0427. Min Act: -0.1700
Data Index: 3120280 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0269. Min Act: -0.1700
Data Index: 1945319 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0427. Min Act: -0.1700
Data Index: 4644904 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0743. Min Act: -0.1700
Data Index: 2530299 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0269. Min Act: -0.1700
Data Index: 3839866 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1373. Min Range: -3.1373
Max Act: 3.0269. Min Act: -0.1700
Data Index: 4605135 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19