Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0897. Min Range: -3.0897
Max Act: 3.0897. Min Act: -0.1700
Data Index: 7755809 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0897. Min Range: -3.0897
Max Act: 3.0424. Min Act: -0.1700
Data Index: 8345733 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0897. Min Range: -3.0897
Max Act: 3.0266. Min Act: -0.1700
Data Index: 241013 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0897. Min Range: -3.0897
Max Act: 3.0424. Min Act: -0.1700
Data Index: 1708595 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9950. Min Act: -0.1700
Data Index: 6330011 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9792. Min Act: -0.1700
Data Index: 8187586 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9634. Min Act: -0.1700
Data Index: 5042941 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 3917229 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9475. Min Act: -0.1700
Data Index: 734859 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 2025885 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 2025447 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9475. Min Act: -0.1700
Data Index: 2164341 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 896036 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 5208646 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9000. Min Act: -0.1700
Data Index: 5496713 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9158. Min Act: -0.1700
Data Index: 7808411 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 1108147 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9158. Min Act: -0.1700
Data Index: 5857339 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9317. Min Act: -0.1700
Data Index: 6364353 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0897. Min Range: -3.0897
Max Act: 2.9000. Min Act: -0.1700
Data Index: 4275616 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19