Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 510 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.6200. Min Act: -0.1700
Data Index: 2841597 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.7137. Min Act: -0.1700
Data Index: 8695411 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.5575. Min Act: -0.1700
Data Index: 8032280 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.5262. Min Act: -0.1700
Data Index: 1335189 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.5262. Min Act: -0.1700
Data Index: 3136422 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.5262. Min Act: -0.1700
Data Index: 8736735 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.5262. Min Act: -0.1700
Data Index: 4498643 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.4012. Min Act: -0.1700
Data Index: 6396749 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.4012. Min Act: -0.1700
Data Index: 4539141 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.4012. Min Act: -0.1700
Data Index: 3848055 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.3387. Min Act: -0.1699
Data Index: 4385521 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.4012. Min Act: -0.1700
Data Index: 1739935 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.3075. Min Act: -0.1700
Data Index: 6459273 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.3700. Min Act: -0.1700
Data Index: 1419683 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.2762. Min Act: -0.1700
Data Index: 5309256 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.2450. Min Act: -0.1700
Data Index: 7425762 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.2450. Min Act: -0.1700
Data Index: 368833 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.3700. Min Act: -0.1700
Data Index: 5095703 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.2450. Min Act: -0.1700
Data Index: 3728240 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7137. Min Range: -5.7137
Max Act: 5.1825. Min Act: -0.1700
Data Index: 6700588 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19