Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5651 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0326. Min Range: -6.0326
Max Act: 6.0326. Min Act: -0.1700
Data Index: 5296721 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5296725 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.9701. Min Act: -0.1700
Data Index: 5551733 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4071506 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.8451. Min Act: -0.1700
Data Index: 8649649 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.9076. Min Act: -0.1700
Data Index: 876339 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.8139. Min Act: -0.1700
Data Index: 7205256 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.8139. Min Act: -0.1700
Data Index: 2103390 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.7514. Min Act: -0.1700
Data Index: 4818219 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.7514. Min Act: -0.1700
Data Index: 6455504 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.7826. Min Act: -0.1700
Data Index: 7419314 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.7201. Min Act: -0.1700
Data Index: 8508388 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6889. Min Act: -0.1700
Data Index: 6280016 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6889. Min Act: -0.1700
Data Index: 113280 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6889. Min Act: -0.1700
Data Index: 8377693 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6889. Min Act: -0.1700
Data Index: 6573851 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6264. Min Act: -0.1700
Data Index: 721229 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6264. Min Act: -0.1700
Data Index: 197906 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6264. Min Act: -0.1700
Data Index: 8152544 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0326. Min Range: -6.0326
Max Act: 5.6264. Min Act: -0.1700
Data Index: 3063386 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19