Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 3357388 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 4520202 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0915. Min Act: -0.1700
Data Index: 2304780 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0603. Min Act: -0.1700
Data Index: 3494565 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7719752 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7475849 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0603. Min Act: -0.1700
Data Index: 1959900 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0915. Min Range: -5.0915
Max Act: 5.0290. Min Act: -0.1700
Data Index: 4633137 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9665. Min Act: -0.1700
Data Index: 215046 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 8490011 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 2365379 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9665. Min Act: -0.1700
Data Index: 255467 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9665. Min Act: -0.1700
Data Index: 2056558 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 1006124 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 6451513 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 6331421 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 5798066 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9978. Min Act: -0.1700
Data Index: 3563497 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1388234 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0915. Min Range: -5.0915
Max Act: 4.9665. Min Act: -0.1700
Data Index: 1415137 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19