Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.3096. Min Act: -0.1700
Data Index: 5677600 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.2471. Min Act: -0.1700
Data Index: 4298678 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.2471. Min Act: -0.1700
Data Index: 3064252 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.2783. Min Act: -0.1700
Data Index: 399686 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.2158. Min Act: -0.1700
Data Index: 337339 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.2158. Min Act: -0.1700
Data Index: 1045918 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1846. Min Act: -0.1700
Data Index: 337347 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1220. Min Act: -0.1700
Data Index: 2989256 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1220. Min Act: -0.1700
Data Index: 4970753 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1533. Min Act: -0.1700
Data Index: 4867512 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1533. Min Act: -0.1700
Data Index: 337344 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1220. Min Act: -0.1700
Data Index: 337349 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0908. Min Act: -0.1700
Data Index: 337340 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1220. Min Act: -0.1700
Data Index: 2368634 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.1220. Min Act: -0.1700
Data Index: 4094548 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0908. Min Act: -0.1700
Data Index: 337346 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0908. Min Act: -0.1700
Data Index: 5677619 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0908. Min Act: -0.1700
Data Index: 4367508 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0283. Min Act: -0.1700
Data Index: 5987960 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3096. Min Range: -4.3096
Max Act: 4.0283. Min Act: -0.1700
Data Index: 2096728 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19