Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1875. Min Range: -11.1875
Max Act: 11.1875. Min Act: -0.1700
Data Index: 5974188 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.3750. Min Act: -0.1700
Data Index: 5110277 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.3750. Min Act: -0.1700
Data Index: 4321330 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.3125. Min Act: -0.1700
Data Index: 4539185 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.1875. Min Act: -0.1700
Data Index: 5259295 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.1250. Min Act: -0.1700
Data Index: 8150291 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.0625. Min Act: -0.1700
Data Index: 2235737 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.0625. Min Act: -0.1700
Data Index: 4509456 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1875. Min Range: -11.1875
Max Act: 10.0625. Min Act: -0.1700
Data Index: 6125266 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.9375. Min Act: -0.1700
Data Index: 442675 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.9375. Min Act: -0.1700
Data Index: 6304069 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.8750. Min Act: -0.1700
Data Index: 5599217 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.8125. Min Act: -0.1700
Data Index: 3687476 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.8125. Min Act: -0.1700
Data Index: 7373191 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.7500. Min Act: -0.1700
Data Index: 1148973 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.7500. Min Act: -0.1700
Data Index: 7853880 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.7500. Min Act: -0.1700
Data Index: 891395 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.6875. Min Act: -0.1700
Data Index: 11323 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.6875. Min Act: -0.1700
Data Index: 7429339 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1875. Min Range: -11.1875
Max Act: 9.6250. Min Act: -0.1700
Data Index: 3886796 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19