Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3764 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.6022. Min Act: -0.1700
Data Index: 6322247 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5710. Min Act: -0.1700
Data Index: 3242550 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5710. Min Act: -0.1700
Data Index: 3822150 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 8733498 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5397. Min Act: -0.1700
Data Index: 3219897 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 6254604 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 7030771 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 6854378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 1463760 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 1161662 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 114502 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 215289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.5085. Min Act: -0.1700
Data Index: 6976450 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 6282005 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5435869 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4460. Min Act: -0.1700
Data Index: 2425535 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 1838413 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 5460172 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 6265801 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6022. Min Range: -4.6022
Max Act: 4.4772. Min Act: -0.1700
Data Index: 8264282 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19