Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.7842. Min Act: -0.1700
Data Index: 3559438 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.7529. Min Act: -0.1700
Data Index: 680250 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.7217. Min Act: -0.1700
Data Index: 4923590 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.6904. Min Act: -0.1700
Data Index: 8091126 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.6279. Min Act: -0.1700
Data Index: 2343664 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.6279. Min Act: -0.1700
Data Index: 1873472 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.6279. Min Act: -0.1700
Data Index: 3298740 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5967. Min Act: -0.1700
Data Index: 3781027 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5654. Min Act: -0.1700
Data Index: 7295405 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5342. Min Act: -0.1700
Data Index: 5318955 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5342. Min Act: -0.1700
Data Index: 641121 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5342. Min Act: -0.1700
Data Index: 2326235 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5342. Min Act: -0.1700
Data Index: 6515922 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5654. Min Act: -0.1700
Data Index: 74157 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5342. Min Act: -0.1700
Data Index: 5494362 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5029. Min Act: -0.1700
Data Index: 1529756 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5029. Min Act: -0.1700
Data Index: 680283 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5029. Min Act: -0.1700
Data Index: 5349949 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5029. Min Act: -0.1700
Data Index: 3834589 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7842. Min Range: -4.7842
Max Act: 4.5029. Min Act: -0.1700
Data Index: 3595647 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19