Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5347 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.8433. Min Act: -0.1700
Data Index: 122209 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.8433. Min Act: -0.1700
Data Index: 4963212 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.7808. Min Act: -0.1700
Data Index: 3691518 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.7495. Min Act: -0.1700
Data Index: 1740948 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.7026. Min Act: -0.1700
Data Index: 6895511 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.7182. Min Act: -0.1700
Data Index: 6915256 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.7026. Min Act: -0.1700
Data Index: 7331266 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.6713. Min Act: -0.1700
Data Index: 207510 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.6243. Min Act: -0.1700
Data Index: 16390 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.6400. Min Act: -0.1700
Data Index: 1054093 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.6087. Min Act: -0.1700
Data Index: 301425 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5930. Min Act: -0.1700
Data Index: 1084866 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5774. Min Act: -0.1700
Data Index: 1925321 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5774. Min Act: -0.1700
Data Index: 5871049 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5617. Min Act: -0.1700
Data Index: 1350830 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5617. Min Act: -0.1700
Data Index: 7840961 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5461. Min Act: -0.1700
Data Index: 871237 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5461. Min Act: -0.1700
Data Index: 4425927 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5461. Min Act: -0.1700
Data Index: 659530 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8433. Min Range: -3.8433
Max Act: 3.5461. Min Act: -0.1700
Data Index: 54957 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19