Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7947. Min Act: -0.1700
Data Index: 4560548 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.8260. Min Act: -0.1700
Data Index: 151804 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7322. Min Act: -0.1700
Data Index: 2799000 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7322. Min Act: -0.1700
Data Index: 7620327 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7947. Min Act: -0.1700
Data Index: 8012292 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7635. Min Act: -0.1700
Data Index: 6731948 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7322. Min Act: -0.1700
Data Index: 8643006 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7635. Min Act: -0.1700
Data Index: 1052549 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7635. Min Act: -0.1700
Data Index: 1159427 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7322. Min Act: -0.1700
Data Index: 377954 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7947. Min Act: -0.1700
Data Index: 6665838 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7010. Min Act: -0.1700
Data Index: 4713595 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7010. Min Act: -0.1700
Data Index: 1828435 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7010. Min Act: -0.1700
Data Index: 6403100 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7322. Min Act: -0.1700
Data Index: 5368512 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.6697. Min Act: -0.1700
Data Index: 4873164 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.7010. Min Act: -0.1700
Data Index: 5174340 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.6385. Min Act: -0.1700
Data Index: 3983173 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.6697. Min Act: -0.1700
Data Index: 3161700 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8260. Min Range: -4.8260
Max Act: 4.6697. Min Act: -0.1700
Data Index: 5991038 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19