Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1011. Min Range: -8.1011
Max Act: 8.1011. Min Act: -0.1700
Data Index: 361874 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1011. Min Range: -8.1011
Max Act: 8.1011. Min Act: -0.1700
Data Index: 7736305 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.9136. Min Act: -0.1700
Data Index: 6593142 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.8511. Min Act: -0.1700
Data Index: 2985802 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.7886. Min Act: -0.1700
Data Index: 5341011 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.7573. Min Act: -0.1700
Data Index: 886253 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.7573. Min Act: -0.1700
Data Index: 4763141 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.7573. Min Act: -0.1700
Data Index: 6113565 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.6636. Min Act: -0.1700
Data Index: 3104279 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.6636. Min Act: -0.1700
Data Index: 2691885 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.6323. Min Act: -0.1700
Data Index: 430930 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.6323. Min Act: -0.1700
Data Index: 5881760 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.6011. Min Act: -0.1700
Data Index: 6269409 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.5698. Min Act: -0.1700
Data Index: 2454377 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.5698. Min Act: -0.1700
Data Index: 1312557 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.5386. Min Act: -0.1700
Data Index: 8502596 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.5698. Min Act: -0.1700
Data Index: 6589918 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.5073. Min Act: -0.1700
Data Index: 1224865 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.4448. Min Act: -0.1700
Data Index: 5708605 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1011. Min Range: -8.1011
Max Act: 7.4448. Min Act: -0.1700
Data Index: 6542485 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19