Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.4014. Min Act: -0.1700
Data Index: 6743105 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.3077. Min Act: -0.1700
Data Index: 3725398 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.1826. Min Act: -0.1700
Data Index: 3707841 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.1514. Min Act: -0.1700
Data Index: 5856427 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.1201. Min Act: -0.1700
Data Index: 6953094 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0889. Min Act: -0.1700
Data Index: 823219 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0576. Min Act: -0.1700
Data Index: 3933149 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0264. Min Act: -0.1700
Data Index: 8598854 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0576. Min Act: -0.1700
Data Index: 4188970 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0264. Min Act: -0.1700
Data Index: 5598955 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0264. Min Act: -0.1700
Data Index: 1100799 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4014. Min Range: -4.4014
Max Act: 4.0264. Min Act: -0.1700
Data Index: 3465402 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9638. Min Act: -0.1700
Data Index: 5338715 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9951. Min Act: -0.1700
Data Index: 3702900 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9638. Min Act: -0.1700
Data Index: 8759325 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9951. Min Act: -0.1700
Data Index: 4859787 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9951. Min Act: -0.1700
Data Index: 8023622 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9951. Min Act: -0.1700
Data Index: 7933405 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9638. Min Act: -0.1700
Data Index: 4287664 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4014. Min Range: -4.4014
Max Act: 3.9638. Min Act: -0.1700
Data Index: 7189517 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19