Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1731 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1245. Min Range: -3.1245
Max Act: 3.1245. Min Act: -0.1700
Data Index: 738213 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1245. Min Range: -3.1245
Max Act: 3.0457. Min Act: -0.1700
Data Index: 2256325 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1245. Min Range: -3.1245
Max Act: 3.0299. Min Act: -0.1700
Data Index: 2174248 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1245. Min Range: -3.1245
Max Act: 3.0141. Min Act: -0.1700
Data Index: 7115050 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.9983. Min Act: -0.1700
Data Index: 6623954 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.9667. Min Act: -0.1700
Data Index: 8204503 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.9350. Min Act: -0.1700
Data Index: 6218930 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.9033. Min Act: -0.1700
Data Index: 3742641 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8875. Min Act: -0.1700
Data Index: 8041575 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8716. Min Act: -0.1700
Data Index: 6716419 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8875. Min Act: -0.1700
Data Index: 2846107 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.9033. Min Act: -0.1700
Data Index: 7489142 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8716. Min Act: -0.1700
Data Index: 547850 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8716. Min Act: -0.1700
Data Index: 6182271 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8557. Min Act: -0.1700
Data Index: 2664907 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8398. Min Act: -0.1700
Data Index: 4153777 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8557. Min Act: -0.1700
Data Index: 151008 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8557. Min Act: -0.1700
Data Index: 5159957 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.8239. Min Act: -0.1700
Data Index: 5260893 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1245. Min Range: -3.1245
Max Act: 2.7921. Min Act: -0.1700
Data Index: 2108127 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19