Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 354 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1007. Min Range: -8.1007
Max Act: 8.1007. Min Act: -0.1700
Data Index: 3641256 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.3507. Min Act: -0.1700
Data Index: 606496 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.3507. Min Act: -0.1700
Data Index: 1189804 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.2882. Min Act: -0.1700
Data Index: 2242769 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1945. Min Act: -0.1700
Data Index: 269465 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.2257. Min Act: -0.1700
Data Index: 5380524 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1320. Min Act: -0.1700
Data Index: 8159109 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1632. Min Act: -0.1700
Data Index: 3952205 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 4694222 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1320. Min Act: -0.1700
Data Index: 5745686 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1632. Min Act: -0.1700
Data Index: 5113932 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1007. Min Act: -0.1700
Data Index: 4751884 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.1320. Min Act: -0.1700
Data Index: 6901539 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0695. Min Act: -0.1700
Data Index: 6027335 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0695. Min Act: -0.1700
Data Index: 1674492 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0695. Min Act: -0.1700
Data Index: 8540072 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0695. Min Act: -0.1700
Data Index: 2111937 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 7078281 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 6953613 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1007. Min Range: -8.1007
Max Act: 7.0382. Min Act: -0.1700
Data Index: 4490745 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19