Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.9836. Min Act: -0.1700
Data Index: 2031119 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.8586. Min Act: -0.1700
Data Index: 7396288 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.8274. Min Act: -0.1700
Data Index: 2884975 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7649. Min Act: -0.1700
Data Index: 2632593 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7336. Min Act: -0.1700
Data Index: 4057572 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7336. Min Act: -0.1700
Data Index: 4410659 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7024. Min Act: -0.1700
Data Index: 7668436 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7024. Min Act: -0.1700
Data Index: 818239 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6711. Min Act: -0.1700
Data Index: 7674049 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.7024. Min Act: -0.1700
Data Index: 3709883 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6711. Min Act: -0.1700
Data Index: 1877217 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6711. Min Act: -0.1700
Data Index: 5819877 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6086. Min Act: -0.1700
Data Index: 1510168 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6399. Min Act: -0.1700
Data Index: 7553743 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.5774. Min Act: -0.1700
Data Index: 6047231 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6086. Min Act: -0.1700
Data Index: 5183633 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.6086. Min Act: -0.1700
Data Index: 2207664 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.5774. Min Act: -0.1700
Data Index: 7912761 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.5774. Min Act: -0.1700
Data Index: 6561361 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9836. Min Range: -5.9836
Max Act: 5.5149. Min Act: -0.1700
Data Index: 7792310 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19