Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9846. Min Act: -0.1700
Data Index: 3184393 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.9221. Min Act: -0.1700
Data Index: 7057932 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 42029 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 4109752 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 2121803 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7971. Min Act: -0.1700
Data Index: 7255789 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.8596. Min Act: -0.1700
Data Index: 4972129 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 5063409 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 4528503 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.7346. Min Act: -0.1700
Data Index: 7394253 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 4364907 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 3876267 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 5405151 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 5184775 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 2297416 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 750304 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6721. Min Act: -0.1700
Data Index: 8430780 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6096. Min Act: -0.1700
Data Index: 1548585 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6096. Min Act: -0.1700
Data Index: 3423388 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9846. Min Range: -8.9846
Max Act: 8.6096. Min Act: -0.1700
Data Index: 2882349 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19