Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 178 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1235. Min Range: -5.1235
Max Act: 5.1235. Min Act: -0.1700
Data Index: 818573 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1235. Min Range: -5.1235
Max Act: 5.0923. Min Act: -0.1700
Data Index: 8249363 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1235. Min Range: -5.1235
Max Act: 5.0298. Min Act: -0.1700
Data Index: 4409548 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9673. Min Act: -0.1700
Data Index: 8725374 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9673. Min Act: -0.1700
Data Index: 393497 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9985. Min Act: -0.1700
Data Index: 1344315 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 3746788 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 1744028 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 458087 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 7742214 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9048. Min Act: -0.1700
Data Index: 6747760 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9048. Min Act: -0.1700
Data Index: 4985022 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 7526041 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9360. Min Act: -0.1700
Data Index: 5015031 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9048. Min Act: -0.1700
Data Index: 906911 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.8423. Min Act: -0.1700
Data Index: 38725 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.9048. Min Act: -0.1700
Data Index: 1368522 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.8735. Min Act: -0.1700
Data Index: 270048 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.8735. Min Act: -0.1700
Data Index: 4065029 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1235. Min Range: -5.1235
Max Act: 4.8423. Min Act: -0.1700
Data Index: 282332 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19