Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.8009. Min Act: -0.1700
Data Index: 3774128 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.7540. Min Act: -0.1700
Data Index: 7026138 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.6915. Min Act: -0.1700
Data Index: 3479659 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.6289. Min Act: -0.1700
Data Index: 761943 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.5819. Min Act: -0.1700
Data Index: 4723955 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.5350. Min Act: -0.1700
Data Index: 3175526 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.5506. Min Act: -0.1700
Data Index: 77097 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.5036. Min Act: -0.1700
Data Index: 1552269 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4880. Min Act: -0.1700
Data Index: 2224697 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 3406421 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 6336875 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 6548092 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 739413 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 6758836 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4566. Min Act: -0.1700
Data Index: 1651162 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4410. Min Act: -0.1700
Data Index: 7734504 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4723. Min Act: -0.1700
Data Index: 6536200 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4566. Min Act: -0.1700
Data Index: 458668 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4880. Min Act: -0.1700
Data Index: 5680946 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8009. Min Range: -3.8009
Max Act: 3.4410. Min Act: -0.1700
Data Index: 3490103 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19