Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0416. Min Range: -5.0416
Max Act: 5.0416. Min Act: -0.1700
Data Index: 1748187 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0416. Min Range: -5.0416
Max Act: 5.0104. Min Act: -0.1700
Data Index: 2166460 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.8854. Min Act: -0.1700
Data Index: 913438 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.8229. Min Act: -0.1700
Data Index: 1121712 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.8229. Min Act: -0.1700
Data Index: 1121727 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 4355056 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6055186 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6165592 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 330713 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 7574838 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 8317690 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7291. Min Act: -0.1700
Data Index: 1920305 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7291. Min Act: -0.1700
Data Index: 1121711 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 4283912 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7291. Min Act: -0.1700
Data Index: 4086496 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7603. Min Act: -0.1700
Data Index: 1121714 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.6978. Min Act: -0.1700
Data Index: 2198394 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.6978. Min Act: -0.1700
Data Index: 1121716 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.6978. Min Act: -0.1700
Data Index: 4248698 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0416. Min Range: -5.0416
Max Act: 4.7291. Min Act: -0.1700
Data Index: 504899 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19