Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 797 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.9237. Min Act: -0.1700
Data Index: 6497753 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.7361. Min Act: -0.1700
Data Index: 4627718 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.7361. Min Act: -0.1700
Data Index: 829571 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.6892. Min Act: -0.1700
Data Index: 410567 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.6579. Min Act: -0.1700
Data Index: 1755783 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5796. Min Act: -0.1700
Data Index: 1097261 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5796. Min Act: -0.1700
Data Index: 4130894 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5796. Min Act: -0.1700
Data Index: 8706039 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5640. Min Act: -0.1700
Data Index: 2788842 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5170. Min Act: -0.1700
Data Index: 3543346 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5170. Min Act: -0.1700
Data Index: 1198543 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5327. Min Act: -0.1700
Data Index: 6758379 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5014. Min Act: -0.1700
Data Index: 7256224 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5014. Min Act: -0.1700
Data Index: 2019807 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5014. Min Act: -0.1700
Data Index: 7509491 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5170. Min Act: -0.1700
Data Index: 3554844 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.4857. Min Act: -0.1700
Data Index: 4113469 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.4700. Min Act: -0.1700
Data Index: 2370107 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.4700. Min Act: -0.1700
Data Index: 7022264 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9237. Min Range: -3.9237
Max Act: 3.5014. Min Act: -0.1700
Data Index: 8759856 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19