Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0968. Min Range: -9.0968
Max Act: 9.0968. Min Act: -0.1700
Data Index: 595840 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.8468. Min Act: -0.1700
Data Index: 3751652 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 4816296 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7843. Min Act: -0.1700
Data Index: 1526424 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7843. Min Act: -0.1700
Data Index: 975231 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 7332398 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 5160573 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 332900 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 1055887 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.7218. Min Act: -0.1700
Data Index: 5811712 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.6593. Min Act: -0.1700
Data Index: 7173189 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.6593. Min Act: -0.1700
Data Index: 7811683 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.6593. Min Act: -0.1700
Data Index: 536346 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.5968. Min Act: -0.1700
Data Index: 7108556 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.5343. Min Act: -0.1700
Data Index: 6888777 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.4718. Min Act: -0.1700
Data Index: 4060753 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.4718. Min Act: -0.1700
Data Index: 5982765 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.4718. Min Act: -0.1700
Data Index: 1887676 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.4718. Min Act: -0.1700
Data Index: 3262272 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0968. Min Range: -9.0968
Max Act: 8.3468. Min Act: -0.1700
Data Index: 5490562 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19